arxiv: 2604.12579 · v2 · submitted 2026-04-14 · 💻 cs.LG

Recognition: 2 theorem links

· Lean Theorem

EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts

Cuntai Guan, Guanxiang Huang, Motoaki Kawanabe, Qibin Zhao, Runhe Zhou, Shanglin Li, Xinliang Zhou, Yi Ding

Authors on Pith no claims yet

Pith reviewed 2026-05-12 00:51 UTC · model grok-4.3

classification 💻 cs.LG

keywords EEGmultimodal learninghyperbolic geometrymixture of expertsemotion recognitionsleep stagingcognitive assessment

0 comments

The pith

EEG-MoCE assigns each modality to its own learnable-curvature hyperbolic expert and fuses them with curvature-aware weighting to capture hierarchical structures in brain signals.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes EEG-MoCE for multimodal learning that combines EEG with signals such as facial expressions to assess mental states. It starts from the observation that these modalities contain hierarchical structures arising from cognitive processes, which flat Euclidean space represents poorly while hyperbolic space matches through its exponential volume growth. Each modality receives its own expert whose curvature is learned during training so the geometry fits the data, after which a fusion step weights contributions according to how strongly each expert's curvature signals rich hierarchy. The resulting model is tested on standard benchmarks and reported to reach higher performance than prior approaches on emotion recognition, sleep staging, and cognitive assessment. A reader would care because more faithful geometric modeling of brain data could support more reliable clinical tools for mental-state monitoring.

Core claim

EEG-MoCE places each input modality into a dedicated expert inside a hyperbolic space whose curvature is learned independently, thereby adapting the geometry to the modality's intrinsic hierarchy. Curvature-aware fusion then combines the expert outputs by dynamically emphasizing those modalities whose learned curvature indicates greater hierarchical content. Experiments on benchmark datasets establish state-of-the-art results across emotion recognition, sleep staging, and cognitive assessment tasks.

What carries the argument

The mixture-of-curvature experts operating in hyperbolic space, where each expert learns its own curvature and the fusion weights are derived from those curvatures to highlight modalities carrying richer hierarchical information.

If this is right

Multimodal EEG systems achieve higher accuracy on emotion classification than Euclidean baselines.
Sleep staging benefits from dynamic emphasis on modalities whose geometry encodes stronger hierarchy.
Cognitive assessment tasks obtain improved performance when curvature-aware weighting is applied.
The same adaptive-geometry principle extends to other EEG-based mental-state pipelines.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Curvature values learned for different modalities might later be inspected to quantify how much hierarchy each contributes.
If the curvature-learning step remains stable across patient populations, the framework could support real-time neurotechnology devices.
The approach supplies a concrete testbed for checking whether hyperbolic geometry systematically outperforms Euclidean geometry on hierarchical neuroscience data.

Load-bearing premise

That EEG and the other modalities possess hierarchical structures best captured by hyperbolic geometry when each modality is allowed its own independently learned curvature.

What would settle it

An ablation experiment that replaces the learnable per-modality curvatures with a single shared curvature or switches to Euclidean space while keeping all other components fixed, and finds no accuracy gain on the same emotion-recognition, sleep-staging, or cognitive-assessment benchmarks.

Figures

Figures reproduced from arXiv: 2604.12579 by Cuntai Guan, Guanxiang Huang, Motoaki Kawanabe, Qibin Zhao, Runhe Zhou, Shanglin Li, Xinliang Zhou, Yi Ding.

**Figure 1.** Figure 1: Euclidean vs. hyperbolic geometry for hierarchical data. Euclidean space is flat and tends to under-represent hierarchical branching; hyperbolic space exhibits exponential volume growth and better preserves tree-like separation. Hyperbolic geometry is informative for multimodal learning, where modalities may differ in how strongly hierarchical their underlying structure is. tive processes (Bell & Cuevas,… view at source ↗

**Figure 2.** Figure 2: Architecture of EEG-MoCE on EAV dataset. Other datasets use the same overall architecture, with only modality encoders adapted. (a) Modality-specific hyperbolic experts: each modality (e.g., EEG, audio, video) is encoded by an expert that embeds inputs in its own learnable-curvature hyperbolic space. (b) Curvature-oriented fusion: expert representations are aggregated by a curvature-aware scheme, combining… view at source ↗

**Figure 4.** Figure 4: Ablation of hyperbolic components on the EAV dataset, focusing on learnable curvature and curvature-oriented multimodal fusion (COMF). All fusion variants use learnable curvatures to isolate the effect of the fusion mechanism. Our proposed method achieves the best performance, demonstrating the complementary benefits of learnable curvatures and COMF. The results in [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗

**Figure 3.** Figure 3: t-SNE of fused features on EAV dataset. Hyperbolic encoder and fusion variant produces more compact and betterseparated emotion clusters than the Euclidean baseline variant, illustrating improved class separability by hyperbolic geometry. The results demonstrate that hyperbolic geometry in both encoder and fusion stages is essential for optimal performance, with each component contributing complementary … view at source ↗

read the original abstract

Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential. The effectiveness of such paradigms largely depends on the representation learning on heterogeneous modalities. For EEG-based paradigms, one promising approach is to leverage their hierarchical structures, as recent studies have shown that both EEG and associated modalities (e.g., facial expressions) exhibit hierarchical structures reflecting complex cognitive processes. However, Euclidean embeddings struggle to represent these hierarchical structures due to their flat geometry, while hyperbolic spaces, with their exponential growth property, are naturally suited for them. In this work, we propose EEG-MoCE, a novel hyperbolic mixture-of-curvature experts framework designed for multimodal neurotechnology. EEG-MoCE assigns each modality to an expert in a learnable-curvature hyperbolic space, enabling adaptive modeling of its intrinsic geometry. A curvature-aware fusion strategy then dynamically weights experts, emphasizing modalities with richer hierarchical information. Extensive experiments on benchmark datasets demonstrate that EEG-MoCE achieves state-of-the-art performance, including emotion recognition, sleep staging, and cognitive assessment.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper introduces per-modality learnable curvatures in a hyperbolic MoE for EEG multimodal tasks, but the abstract supplies zero numbers or ablations to show the curvatures matter.

read the letter

The main thing to know is that the authors built EEG-MoCE, a mixture-of-experts setup where each modality gets its own expert in a hyperbolic space whose curvature is learned during training, followed by a fusion step that weights experts according to those curvatures. They apply it to emotion recognition, sleep staging, and cognitive assessment from EEG plus other signals. This specific adaptive-curvature formulation for neuro signals is new relative to prior hyperbolic work on hierarchies. The motivation section does a clean job explaining why flat Euclidean embeddings fall short for the tree-like structure in brain data and why hyperbolic geometry's volume growth fits better. The architecture description is straightforward and avoids unnecessary complexity. The soft spots are real and center on missing evidence. The abstract claims state-of-the-art results but shows no tables, no baseline numbers, no statistical tests, and no ablations that isolate learnable curvature from a fixed-curvature hyperbolic MoE or a plain Euclidean version of similar size. Without those, we cannot tell whether the curvatures actually settle at different values across modalities or whether the fusion weights track hierarchical richness instead of noise. The stability worry is also fair: learnable curvatures are known to be sensitive to initialization and can collapse toward zero or produce unstable Möbius operations, yet nothing in the writeup addresses this. The paper is aimed at people working at the overlap of geometric deep learning and multimodal brain-signal processing. A reader who wants to try hyperbolic methods on EEG data could extract a usable architecture sketch from it, but only after the experiments are filled in. It deserves a serious referee because the idea is coherent, the application area is relevant, and the geometric framing engages honestly with existing literature on hyperbolic embeddings. I would send it out for review with a clear request for curvature ablations, stability checks, and full quantitative results.

Referee Report

2 major / 0 minor

Summary. The manuscript proposes EEG-MoCE, a hyperbolic mixture-of-curvature experts framework for EEG-based multimodal learning. Each modality is assigned to an expert operating in its own learnable-curvature hyperbolic space, followed by a curvature-aware fusion mechanism that dynamically weights the experts according to the richness of hierarchical structure in each modality. The authors claim that this architecture yields state-of-the-art performance on benchmark datasets for emotion recognition, sleep staging, and cognitive assessment.

Significance. If the performance claims are rigorously substantiated, the work would add a concrete demonstration that per-modality learnable curvatures and curvature-aware fusion can exploit the exponential volume growth of hyperbolic geometry for heterogeneous neurophysiological signals. This would be of interest to the intersection of geometric deep learning and multimodal brain-computer interfaces, provided the gains are shown to arise from the geometric inductive bias rather than capacity alone.

major comments (2)

[Abstract] Abstract: the claim that EEG-MoCE 'achieves state-of-the-art performance' is unsupported by any numerical results, baseline tables, statistical tests, or ablation studies. Without these data it is impossible to determine whether the reported improvements are attributable to the learnable-curvature experts or to other modeling choices.
[Method / Experiments] Method and Experiments sections: the central modeling assumption—that independently learnable curvatures per modality plus curvature-aware fusion reliably capture richer hierarchical information—lacks any ablation that isolates these components against (i) a fixed-curvature hyperbolic MoE of equal capacity and (ii) a Euclidean MoE baseline. In the absence of such controls, the SOTA claim cannot be distinguished from a simple increase in model flexibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. The comments highlight opportunities to make the performance claims more transparent and to provide stronger evidence isolating the contributions of the proposed components. We address each point below and have revised the manuscript accordingly.

read point-by-point responses

Referee: [Abstract] Abstract: the claim that EEG-MoCE 'achieves state-of-the-art performance' is unsupported by any numerical results, baseline tables, statistical tests, or ablation studies. Without these data it is impossible to determine whether the reported improvements are attributable to the learnable-curvature experts or to other modeling choices.

Authors: We agree that the abstract, as a concise summary, did not include concrete numerical support. The full manuscript contains extensive experimental results, including baseline comparisons, tables, and statistical tests on emotion recognition, sleep staging, and cognitive assessment benchmarks. In the revised version we have updated the abstract to report key quantitative improvements (e.g., accuracy and F1 gains relative to prior SOTA) together with explicit references to the experimental tables and statistical analyses. This makes the SOTA claim directly verifiable from the abstract while preserving its brevity. revision: yes
Referee: [Method / Experiments] Method and Experiments sections: the central modeling assumption—that independently learnable curvatures per modality plus curvature-aware fusion reliably capture richer hierarchical information—lacks any ablation that isolates these components against (i) a fixed-curvature hyperbolic MoE of equal capacity and (ii) a Euclidean MoE baseline. In the absence of such controls, the SOTA claim cannot be distinguished from a simple increase in model flexibility.

Authors: This observation is correct and points to a genuine gap in the original submission. To isolate the effect of learnable per-modality curvatures and curvature-aware fusion from mere capacity increases, we have added two controlled ablation studies in the revised Experiments section: (i) a fixed-curvature hyperbolic mixture-of-experts model with identical expert count and parameter budget, and (ii) a Euclidean mixture-of-experts baseline matched in capacity. The new results show that the learnable-curvature variant consistently outperforms both controls, indicating that the performance gains arise from the geometric inductive bias rather than flexibility alone. Corresponding tables and analysis have been inserted. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected in derivation chain

full rationale

The paper introduces EEG-MoCE as a novel framework that assigns modalities to experts in learnable-curvature hyperbolic spaces and applies curvature-aware fusion, motivated by the exponential growth property of hyperbolic geometry for hierarchical structures in EEG and related modalities. This motivation is drawn from general properties of hyperbolic spaces and cited recent studies on hierarchical structures, without any reduction of the proposed method or its performance claims to fitted parameters by construction, self-referential uniqueness theorems, or ansatz smuggled via self-citation. The central results are empirical SOTA performance on external benchmarks (emotion recognition, sleep staging, cognitive assessment), which are independent of the model definition itself. No load-bearing steps in the abstract or described method equate outputs to inputs via self-definition or statistical forcing. The derivation remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that hyperbolic geometry is naturally suited to hierarchical EEG structures, plus free parameters for per-expert curvatures and dynamic fusion weights; no new physical entities are postulated.

free parameters (2)

learnable curvatures
One curvature per modality expert, optimized during training to adapt to each data type's geometry.
curvature-aware fusion weights
Dynamically computed weights that emphasize experts based on their learned curvatures.

axioms (1)

domain assumption Hyperbolic spaces are naturally suited for representing hierarchical structures due to their exponential growth property.
Explicitly invoked in the abstract as the geometric motivation for the framework.

pith-pipeline@v0.9.0 · 5509 in / 1282 out tokens · 25811 ms · 2026-05-12T00:51:32.867093+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost Jcost definition and CostAlphaLog echoes
hyperbolic spaces, with their exponential growth property, are naturally suited for them... per-modality experts with learnable curvatures... curvature magnitude serves as a learned geometric indicator of hierarchical complexity... τ(m)=τ0/√|K(m)|... λ·ϕ(K(j)) curvature prior
IndisputableMonolith/Foundation/AlexanderDuality alexander_duality_circle_linking and SphereAdmitsCircleLinking echoes
δ-hyperbolicity... lower δrel indicates stronger hierarchical structure... Lorentz model... expK and logK maps... weighted Fréchet mean

Reference graph

Works this paper leans on

74 extracted references · 74 canonical work pages · 1 internal anchor

[1]

Aboalayon, K. A. I., Faezipour, M., Almuhammadi, W. S., and Moslehpour, S. Sleep stage classification using eeg signal analysis: a comprehensive survey and new investigation. Entropy, 18 0 (9): 0 272, 2016

work page 2016
[2]

Curvature-dimension tradeoff for generalization in hyperbolic space

Alvarado, N., Lobel, H., and Petrache, M. Curvature-dimension tradeoff for generalization in hyperbolic space. In Mathematics of Modern Machine Learning Workshop at NeurIPS, 2023

work page 2023
[3]

EF-Net : Mental state recognition by analyzing multimodal EEG-fNIRS via CNN

Arif, A., Wang, Y., Yin, R., Zhang, X., and Helmy, A. EF-Net : Mental state recognition by analyzing multimodal EEG-fNIRS via CNN . Sensors, 24 0 (6): 0 1889, 2024. doi:10.3390/s24061889

work page doi:10.3390/s24061889 2024
[4]

OpenFace : An open source facial behavior analysis toolkit

Baltrusaitis, T., Robinson, P., and Morency, L.-P. OpenFace : An open source facial behavior analysis toolkit. In IEEE Winter Conference on Applications of Computer Vision (WACV), pp.\ 1--10. IEEE, 2016

work page 2016
[5]

Multimodal machine learning: A survey and taxonomy

Baltru s aitis, T., Ahuja, C., and Morency, L.-P. Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41 0 (2): 0 423--443, 2019. doi:10.1109/TPAMI.2018.2798607

work page doi:10.1109/tpami.2018.2798607 2019
[6]

Fully hyperbolic convolutional neural networks for computer vision

Bdeir, A., Schwethelm, K., and Landwehr, N. Fully hyperbolic convolutional neural networks for computer vision. In International Conference on Learning Representations, 2024

work page 2024
[7]

Bell, M. A. and Cuevas, K. Using eeg to study cognitive development: Issues and practices. Journal of cognition and development, 13 0 (3): 0 281--294, 2012. doi:10.1080/15248372.2012.691143

work page doi:10.1080/15248372.2012.691143 2012
[8]

Stochastic gradient descent on Riemannian manifolds

Bonnabel, S. Stochastic gradient descent on Riemannian manifolds. IEEE Transactions on Automatic Control, 58 0 (9): 0 2217--2229, 2013. doi:10.1109/TAC.2013.2254619

work page doi:10.1109/tac.2013.2254619 2013
[9]

I., Dancsh \'a zy, Z., Szendi, I., Kish, L

B \'u z \'a s, A., Makai, A., Groma, G. I., Dancsh \'a zy, Z., Szendi, I., Kish, L. B., Santa-Maria, A. R., and D \'e r, A. Hierarchical organization of human physical activity. Scientific Reports, 14 0 (1): 0 5981, 2024

work page 2024
[10]

CrossFusionSleepNet : A multimodal deep learning model for automatic sleep stage classification

Cao, Y., Xiang, W., Wei, J., Cao, S., Tian, X., Zhong, J., Fang, X., Luo, B., Lyu, H., and Li, X. CrossFusionSleepNet : A multimodal deep learning model for automatic sleep stage classification. Biomedical Signal Processing and Control, 112: 0 108538, 2026. doi:10.1016/j.bspc.2025.108538

work page doi:10.1016/j.bspc.2025.108538 2026
[11]

Hyperbolic graph convolutional neural networks

Chami, I., Ying, Z., R \'e , C., and Leskovec, J. Hyperbolic graph convolutional neural networks. In Advances in Neural Information Processing Systems, volume 32, 2019

work page 2019
[12]

Multi-scale hyperbolic contrastive learning for cross-subject EEG emotion recognition

Chang, J., Zhang, Z., Qian, Y., and Lin, P. Multi-scale hyperbolic contrastive learning for cross-subject EEG emotion recognition. IEEE Transactions on Affective Computing, 16 0 (3): 0 1716--1731, 2025

work page 2025
[13]

Fully hyperbolic neural networks

Chen, W., Han, X., Lin, Y., Zhao, H., Liu, Z., Li, P., Sun, M., and Zhou, J. Fully hyperbolic neural networks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pp.\ 5672--5686, 2022

work page 2022
[14]

Chen, X. et al. Hyperbolic self-paced multi-expert network for cross-domain few-shot facial expression recognition. IEEE Transactions on Image Processing, 2025 a

work page 2025
[15]

Gyrogroup batch normalization

Chen, Z., Song, Y., Wu, X.-J., and Sebe, N. Gyrogroup batch normalization. In International Conference on Learning Representations, 2025 b

work page 2025
[16]

K., and Behrmann, M

Collins, E., Robinson, A. K., and Behrmann, M. Distinct neural processes for the perception of familiar versus unfamiliar faces along the visual hierarchy revealed by EEG . NeuroImage, 181: 0 120--131, 2018. doi:10.1016/j.neuroimage.2018.06.080

work page doi:10.1016/j.neuroimage.2018.06.080 2018
[17]

Les \'e l \'e ments al \'e atoires de nature quelconque dans un espace distanci \'e

Fr \'e chet, M. Les \'e l \'e ments al \'e atoires de nature quelconque dans un espace distanci \'e . Annales de l'Institut Henri Poincar \'e , 10 0 (4): 0 215--310, 1948

work page 1948
[18]

Hyperbolic neural networks

Ganea, O., B \'e cigneul, G., and Hofmann, T. Hyperbolic neural networks. In Advances in Neural Information Processing Systems, volume 31, 2018

work page 2018
[19]

Hyperbolic groups

Gromov, M. Hyperbolic groups. Springer, New York, 1987

work page 1987
[20]

Learning mixed-curvature representations in product spaces

Gu, A., Sala, F., Gunel, B., and R \'e , C. Learning mixed-curvature representations in product spaces. In International Conference on Learning Representations, 2019

work page 2019
[21]

M., Battaglia, P., Bapst, V., Raposo, D., Santoro, A., and de Freitas, N

Gulcehre, C., Denil, M., Malinowski, M., Razavi, A., Pascanu, R., Hermann, K. M., Battaglia, P., Bapst, V., Raposo, D., Santoro, A., and de Freitas, N. Hyperbolic attention networks. In International Conference on Learning Representations, 2019

work page 2019
[22]

HELM : Hyperbolic large language models via mixture-of-curvature experts

He, N., Anand, R., Madhu, H., Maatouk, A., Krishnaswamy, S., Tassiulas, L., Yang, M., and Ying, R. HELM : Hyperbolic large language models via mixture-of-curvature experts. In Advances in Neural Information Processing Systems, volume 38, 2025

work page 2025
[23]

and Ahissar, M

Hochstein, S. and Ahissar, M. View from the top: Hierarchies and reverse hierarchies in the visual system. Neuron, 36 0 (5): 0 791--804, 2002. doi:10.1016/S0896-6273(02)01091-7

work page doi:10.1016/s0896-6273(02)01091-7 2002
[24]

H., Hammad, A., and Ali, A

Houssein, E. H., Hammad, A., and Ali, A. A. Human emotion recognition from eeg-based brain--computer interface using machine learning: a comprehensive review. Neural Computing and Applications, 34 0 (15): 0 12527--12557, 2022

work page 2022
[25]

MM-DFN : Multimodal dynamic fusion network for emotion recognition in conversations

Hu, D., Hou, X., Wei, L., Jiang, L.-X., and Mo, Y. MM-DFN : Multimodal dynamic fusion network for emotion recognition in conversations. In ICASSP , pp.\ 7037--7041. IEEE , 2022

work page 2022
[26]

XSleepFusion : A dual-stage information bottleneck fusion framework for interpretable multimodal sleep analysis

Hu, S., Wang, Y., Liu, J., and Yang, C. XSleepFusion : A dual-stage information bottleneck fusion framework for interpretable multimodal sleep analysis. Information Fusion, 123: 0 103275, 2025. doi:10.1016/j.inffus.2025.103275

work page doi:10.1016/j.inffus.2025.103275 2025
[27]

and Szegedy, C

Ioffe, S. and Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, pp.\ 448--456. PMLR, 2015

work page 2015
[28]

SalientSleepNet : Multimodal salient wave detection network for sleep staging

Jia, Z., Lin, Y., Wang, J., Wang, X., Xie, P., and Zhang, Y. SalientSleepNet : Multimodal salient wave detection network for sleep staging. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), pp.\ 2614--2620, 2021

work page 2021
[29]

Hypergraph Multi-Modal Learning for EEG-based Emotion Recognition in Conversation

Kang, Z., Li, Y., Gong, S., Zeng, W., Yan, H., Bian, L., Zhang, Z., Siok, W. T., and Wang, N. Hypergraph multi-modal learning for EEG -based emotion recognition in conversation. arXiv preprint arXiv:2502.21154, 2025

work page internal anchor Pith review Pith/arXiv arXiv 2025
[30]

M., and Nunes, U

Khalighi, S., Sousa, T., Santos, J. M., and Nunes, U. ISRUC-Sleep : A comprehensive public dataset for sleep researchers. Computer Methods and Programs in Biomedicine, 124: 0 180--192, 2016

work page 2016
[31]

Hyperbolic image embeddings

Khrulkov, V., Mirvakhabova, L., Ustinova, E., Oseledets, I., and Lempitsky, V. Hyperbolic image embeddings. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.\ 6418--6428, 2020

work page 2020
[32]

J., Hirayama, J.-i., Zhao, Q., and Kawanabe, M

Kobler, R. J., Hirayama, J.-i., Zhao, Q., and Kawanabe, M. SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG . In Advances in Neural Information Processing Systems, volume 35, pp.\ 6219--6235, 2022

work page 2022
[33]

Hyperbolic geometry of complex networks

Krioukov, D., Papadopoulos, F., Kitsak, M., Vahdat, A., and Bogun \'a , M. Hyperbolic geometry of complex networks. Physical Review E, 82 0 (3): 0 036106, 2010

work page 2010
[34]

J., Solon, A

Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., and Lance, B. J. EEGNet : A compact convolutional neural network for EEG -based brain-computer interfaces. Journal of Neural Engineering, 15 0 (5): 0 056013, 2018

work page 2018
[35]

A review of hybrid eeg-based multimodal human--computer interfaces using deep learning: applications, advances, and challenges

Lee, H.-T., Shim, M., Liu, X., Cheon, H.-R., Kim, S.-G., Han, C.-H., and Hwang, H.-J. A review of hybrid eeg-based multimodal human--computer interfaces using deep learning: applications, advances, and challenges. Biomedical Engineering Letters, 15 0 (4): 0 587--618, 2025. doi:10.1007/s13534-025-00469-5

work page doi:10.1007/s13534-025-00469-5 2025
[36]

H., Shomanov, A., Begim, B., Kabidenova, Z., Nyssanbay, A., Yazici, A., and Lee, S.-W

Lee, M. H., Shomanov, A., Begim, B., Kabidenova, Z., Nyssanbay, A., Yazici, A., and Lee, S.-W. EAV : EEG -audio-video dataset for emotion recognition in conversational contexts. Scientific Data, 11 0 (1): 0 1026, 2024

work page 2024
[37]

GA2MIF : Graph and attention based two-stage multi-source information fusion for conversational emotion detection

Li, J., Wang, X., Lv, G., and Zeng, Z. GA2MIF : Graph and attention based two-stage multi-source information fusion for conversational emotion detection. IEEE Transactions on Affective Computing, 15 0 (1): 0 130--143, 2024. doi:10.1109/TAFFC.2023.3261279

work page doi:10.1109/taffc.2023.3261279 2024
[38]

Li, S., Kawanabe, M., and Kobler, R. J. Spdim: Source-free unsupervised conditional and label shift adaptation in eeg. In The Thirteenth International Conference on Learning Representations, 2025

work page 2025
[39]

Heegnet: Hyperbolic embeddings for eeg

Li, S., Chu, S., Ko c , O., Ding, Y., Zhao, Q., Kawanabe, M., and Chen, Z. Heegnet: Hyperbolic embeddings for eeg. In International Conference on Learning Representations, 2026

work page 2026
[40]

Multimodal polysomnography-based automatic sleep stage classification via multiview fusion network

Lin, Y., Wang, M., Hu, F., Cheng, X., and Xu, J. Multimodal polysomnography-based automatic sleep stage classification via multiview fusion network. IEEE Transactions on Instrumentation and Measurement, 73: 0 2504112, 2024. doi:10.1109/TIM.2023.3343781

work page doi:10.1109/tim.2023.3343781 2024
[41]

STA-Net : Spatial--temporal alignment network for hybrid EEG-fNIRS decoding

Liu, M., Yang, B., Meng, L., Zhang, Y., Gao, S., Zan, P., and Xia, X. STA-Net : Spatial--temporal alignment network for hybrid EEG-fNIRS decoding. Information Fusion, 119: 0 103023, 2025. doi:10.1016/j.inffus.2025.103023

work page doi:10.1016/j.inffus.2025.103023 2025
[42]

B., Liang, P

Liu, Z., Shen, Y., Lakshminarasimhan, V. B., Liang, P. P., Zadeh, A., and Morency, L.-P. Efficient low-rank multimodal fusion with modality-specific factors. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp.\ 2247--2256, 2018

work page 2018
[43]

Hierarchical hypercomplex network for multimodal emotion recognition

Lopez, S., Chiarantano, F., et al. Hierarchical hypercomplex network for multimodal emotion recognition. arXiv preprint arXiv:2409.09194, 2024

work page arXiv 2024
[44]

A review of classification algorithms for eeg-based brain--computer interfaces: a 10 year update

Lotte, F., Bougrain, L., Cichocki, A., Clerc, M., Congedo, M., Rakotomamonjy, A., and Yger, F. A review of classification algorithms for eeg-based brain--computer interfaces: a 10 year update. Journal of neural engineering, 15 0 (3): 0 031005, 2018

work page 2018
[45]

doi:10.1007/s11263-024-02043-5

Mettes, P., Ghadimi Atigh, M., Keller-Ressel, M., Gu, J., and Yeung, S. Hyperbolic deep learning in computer vision: A survey. International Journal of Computer Vision, 132 0 (9): 0 3484--3508, 2024. doi:10.1007/s11263-024-02043-5

work page doi:10.1007/s11263-024-02043-5 2024
[46]

The numerical stability of hyperbolic representation learning

Mishne, G., Wan, Z., Wang, Y., and Yang, S. The numerical stability of hyperbolic representation learning. In International Conference on Machine Learning, pp.\ 24925--24949. PMLR, 2023

work page 2023
[47]

H., Tanha, J., and Sharafkhaneh, A

Mostafaei, S. H., Tanha, J., and Sharafkhaneh, A. A novel deep learning model based on transformer and cross modality attention for classification of sleep stages. Journal of Biomedical Informatics, 157: 0 104689, 2024. doi:10.1016/j.jbi.2024.104689

work page doi:10.1016/j.jbi.2024.104689 2024
[48]

D., and Ta, T.-A

Nguyen-Van, T., Le, D. D., and Ta, T.-A. Improving heterogeneous graph learning with weighted mixed-curvature product manifold. arXiv preprint arXiv:2307.04514, 2023

work page arXiv 2023
[49]

and Lopes da Silva, F

Niedermeyer, E. and Lopes da Silva, F. H. (eds.). Electroencephalography: basic principles, clinical applications, and related fields. Lippincott Williams & Wilkins, 5th edition, 2005. ISBN 978-0190228484

work page 2005
[50]

Cross-species affective neuroscience decoding of the primal affective experiences of humans and related animals

Panksepp, J. Cross-species affective neuroscience decoding of the primal affective experiences of humans and related animals. PLoS One, 6 0 (9): 0 e21236, 2011. doi:10.1371/journal.pone.0021236

work page doi:10.1371/journal.pone.0021236 2011
[51]

Hyperbolic deep neural networks: A survey

Peng, W., Varanka, T., Mostafa, A., Shi, H., and Zhao, G. Hyperbolic deep neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44 0 (12): 0 10023--10044, 2022

work page 2022
[52]

and Shanmugam, U

Pillalamarri, R. and Shanmugam, U. A review on eeg-based multimodal learning for emotion recognition. Artificial Intelligence Review, 58 0 (5): 0 131, 2025

work page 2025
[53]

and Zou, D

Qu, E. and Zou, D. Lorentz direct concatenation for stable training in hyperbolic neural networks. In NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022

work page 2022
[54]

Ratcliffe, J. G. Foundations of Hyperbolic Manifolds. Springer, 2006

work page 2006
[55]

Representation tradeoffs for hyperbolic embeddings

Sala, F., De Sa, C., Gu, A., and Re, C. Representation tradeoffs for hyperbolic embeddings. In Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pp.\ 4460--4469. PMLR, 2018

work page 2018
[56]

and Meena, H

Sharma, R. and Meena, H. K. Emerging trends in eeg signal processing: A systematic review. SN Computer Science, 5 0 (4): 0 415, 2024

work page 2024
[57]

Fusion analysis of EEG-fNIRS multimodal brain signals: A multitask classification algorithm incorporating spatial-temporal convolution and dual attention mechanisms

Shi, X., Wang, H., Li, B., Qin, Y., Peng, C., and Lu, Y. Fusion analysis of EEG-fNIRS multimodal brain signals: A multitask classification algorithm incorporating spatial-temporal convolution and dual attention mechanisms. IEEE Transactions on Instrumentation and Measurement, 74: 0 2506312, 2025. doi:10.1109/TIM.2025.3538086

work page doi:10.1109/tim.2025.3538086 2025
[58]

Hyperbolic neural networks++

Shimizu, R., Mukuta, Y., and Harada, T. Hyperbolic neural networks++. In International Conference on Learning Representations, 2021

work page 2021
[59]

u hmann, A., Kim, D.-W., Mehnert, J., Hwang, H.-J., and M \

Shin, J., von L \"u hmann, A., Kim, D.-W., Mehnert, J., Hwang, H.-J., and M \"u ller, K.-R. Simultaneous acquisition of EEG and NIRS during cognitive tasks for an open access dataset. Scientific Data, 5 0 (1): 0 180003, 2018

work page 2018
[60]

Adversarial alignment and graph fusion via information bottleneck for multimodal emotion recognition in conversations

Shou, Y., Meng, T., Ai, W., Zhang, F., Yin, N., and Li, K. Adversarial alignment and graph fusion via information bottleneck for multimodal emotion recognition in conversations. Information Fusion, 112: 0 102590, 2024

work page 2024
[61]

A bidirectional cross-modal transformer representation learning model for EEG-fNIRS multimodal affective BCI

Si, X., Zhang, S., Yang, Z., Yu, J., and Ming, D. A bidirectional cross-modal transformer representation learning model for EEG-fNIRS multimodal affective BCI . Expert Systems with Applications, 266: 0 126081, 2025. doi:10.1016/j.eswa.2024.126081

work page doi:10.1016/j.eswa.2024.126081 2025
[62]

M., Rahman, S., Saeed, S

Siddiqui, M. M., Rahman, S., Saeed, S. H., and Banodia, A. Eeg signals play major role to diagnose sleep disorder. International Journal of Electronics and Computer Science Engineering (IJECSE), 2 0 (2): 0 503--505, 2013

work page 2013
[63]

S., Mountstephens, J., and Teo, J

Suhaimi, N. S., Mountstephens, J., and Teo, J. Eeg-based emotion recognition: a state-of-the-art review of current trends and opportunities. Computational intelligence and neuroscience, 2020 0 (1): 0 8875426, 2020. doi:10.1155/2020/8875426

work page doi:10.1155/2020/8875426 2020
[64]

Functional connectivity between the amygdala and prefrontal cortex underlies processing of emotion ambiguity

Sun, S., Yu, H., Yu, R., and Wang, S. Functional connectivity between the amygdala and prefrontal cortex underlies processing of emotion ambiguity. Translational psychiatry, 13 0 (1): 0 334, 2023. doi:10.1038/s41398-023-02625-w

work page doi:10.1038/s41398-023-02625-w 2023
[65]

Effective phoneme decoding with hyperbolic neural networks for high-performance speech BCIs

Tan, X., Lian, Q., Zhu, J., Zhang, J., Wang, Y., and Qi, Y. Effective phoneme decoding with hyperbolic neural networks for high-performance speech BCIs . IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32: 0 3432--3441, 2024

work page 2024
[66]

Multimodal emotion recognition calibration in conversations

Tu, G., Xiong, F., Liang, B., Wang, H., Zeng, X., and Xu, R. Multimodal emotion recognition calibration in conversations. In Proceedings of the 32nd ACM International Conference on Multimedia, 2024

work page 2024
[67]

Visual information is predictively encoded in occipital alpha/low-beta oscillations

Turner, W., Blom, T., and Hogendoorn, H. Visual information is predictively encoded in occipital alpha/low-beta oscillations. Journal of Neuroscience, 43 0 (30): 0 5537--5545, 2023. doi:10.1523/JNEUROSCI.0135-23.2023

work page doi:10.1523/jneurosci.0135-23.2023 2023
[68]

Ungar, A. A. Analytic Hyperbolic Geometry and Albert Einstein's Special Theory of Relativity . World Scientific, 2nd edition, 2022

work page 2022
[69]

Wallace, B., Knoefel, F., Goubran, R., Zunini, R. A. L., Ren, Z., and Maccosham, A. Eeg/erp: Within episodic assessment framework for cognition. IEEE Transactions on Instrumentation and Measurement, 66 0 (10): 0 2525--2534, 2017

work page 2017
[70]

Modality alignment across trees on heterogeneous hyperbolic manifolds

Wu, W., Fan, X., Wu, Y., Gao, Z., Li, P., Jia, Y., and Harandi, M. Modality alignment across trees on heterogeneous hyperbolic manifolds. In International Conference on Learning Representations, 2026

work page 2026
[71]

Multimodal Multi-loss Fusion Network for Sentiment Analysis

Wu, Z., Gong, Z., Koo, J., and Hirschberg, J. Multimodal multi-loss fusion network for sentiment analysis. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp.\ 3588--3602, Mexico City, Mexico, 2024. Association for Computational Lingu...

work page doi:10.18653/v1/2024.naacl-long.197 2024
[72]

EFDFNet : A multimodal deep fusion network based on feature disentanglement for attention state classification

Xu, H., She, Q., Meng, M., Gao, Y., and Zhang, Y. EFDFNet : A multimodal deep fusion network based on feature disentanglement for attention state classification. Biomedical Signal Processing and Control, 109: 0 108042, 2025. doi:10.1016/j.bspc.2025.108042

work page doi:10.1016/j.bspc.2025.108042 2025
[73]

C., Liu, J., King, I., and Ying, R

Yang, M., Verma, H., Zhang, D. C., Liu, J., King, I., and Ying, R. Hypformer: Exploring efficient transformer fully in hyperbolic space. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp.\ 3770--3781. ACM, 2024. doi:10.1145/3637528.3672039

work page doi:10.1145/3637528.3672039 2024
[74]

Crossmodal translation based meta weight adaption for robust image-text sentiment analysis

Zhang, B., Yuan, Z., Xu, H., and Gao, K. Crossmodal translation based meta weight adaption for robust image-text sentiment analysis. IEEE Transactions on Multimedia, 26: 0 9949--9961, 2024. doi:10.1109/TMM.2024.3405662

work page doi:10.1109/tmm.2024.3405662 2024