REVIEW 5 major objections 5 minor 155 references
Probabilistic Residual Learning for Online Recommendations
T0 review · 5 major / 5 minor · reviewed 2026-08-01 · deepseek-v4-flash
Pith's one-line read PRL claims that any deep recommender can be improved by a plug-and-play Bayesian layer that models the prediction residual and debiases domain confounders via do-calculus.
desk verdict Worth a look for the plug-and-play residual+causal idea, but the printed training algorithm is mathematically undefined for vector confounders; major revision plus code/data release is needed before the claims can be trusted. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The load-bearing mechanism is the residual rating $eR_{ij} = R_{ij} - \hat{R}_{ij}$, combined with the do-calculus debiasing formula of Eq. 28. Users are probabilistically clustered using a Gaussian-mixture prior on the user latent $u_i$, whose cluster assignment $\pi_i$ selects a cluster-specific sub-model. A domain-level confounder $s_m$ (a 'country' embedding in XMRec, a release-year embedding in MovieLens) is modeled as influencing $u_i$, $v_j$, and $eR$, and is inferred with a variational domain-index approximation. At prediction time, Eq. 28 replaces the raw conditional $p(eR | u_i, v_j, s_m)$ with the interventional average $\sum_m p(eR | u_i, v_j, s_m) p(s_m)$, which removes the confounder's direct infl
What would settle it
Run PRL on a synthetic dataset where the generative process includes a known observed domain variable plus a hidden confounder that also affects both user/item latents and the rating. If PRL's post-hoc correction fails to remove the hidden confounder's bias in top-k ranking (compared against a ground-truth no-confounding system), the identifiability claim behind Eq. 28 is falsified. Similarly, on real data with per-domain item popularity measurements, check whether PRL equalizes exposure across domains beyond what a non-causal version does; the paper only reports one such case study.
Extended reading notes
Core claim
The central claim is that cross-domain cold-start recommendation can be reformulated as a plug-and-play probabilistic residual-correction problem. Given any fixed base recommender, PRL learns the residual $eR = R - \hat{R}$ with a hierarchical Bayesian model in which a domain-level confounder $s_m$ affects both user and item latent vectors and the residual, and users are assigned to latent clusters. At inference, for the user's inferred cluster, the residual is predicted by the do-calculus marginalization of Eq. 28, $p^{(k)}(eR | do(u_i), do(v_j)) = \sum_m p^{(k)}(eR | u_i, v_j, s_m) p(s_m)$, which the paper argues cuts the spurious effect of the domain factor. Experiments on XMRec (18 countries)
Load-bearing premise
The causal graph assumed in Fig. 2 — that a single domain-level confounder s_m is the only common cause influencing user and item latents and the residual — is load-bearing; if unobserved confounders exist or s_m is not a true confounder, the do-calculus marginalization of Eq. 28 does not recover a true interventional distribution.
Editorial extensions
If this is right
- Any frozen base recommender can be enhanced without retraining it, saving compute in online systems where the base model is already serving traffic.
- The causal marginalization reduces country-specific recommendation bias; the paper's case study on XMRec reports a 38.5% reduction in the imbalance of camera recommendations across countries.
- PRL automatically discovers user clusters that are interpretable, making it possible to inspect which user groups drive the residuals.
- The full causal PRL outperforms the non-causal version across all reported base models, splits, and cutoff values, indicating the debiasing step is the main contributor to the gains.
- The gains persist even when the base model is scaled up to roughly match PRL's parameter count, suggesting the improvement is structural rather than a capacity artifact.
Reading between the lines
- The residual-correction recipe could transfer to other frozen prediction models (e.g., ranking, click-through rate, forecasting) where retraining is too expensive, using the same cluster-and-debias pattern.
- Real markets likely have multiple confounders at once; extending PRL to a vector-valued s_m and testing whether additional debiasing helps would be a natural next step.
- Because the clusters form around residual errors, they could double as a diagnostic tool: clusters with concentrated large residuals may reveal where the base model is systematically blind, pointing to targeted fixes.
- A synthetic experiment with known ground-truth confounders would directly test whether Eq. 28 actually recovers the interventional distribution; the paper does not report such a validation.
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper proposes Probabilistic Residual Learning (PRL), a plug-and-play framework that models the residual between a fixed base recommender's predictions and ground-truth ratings using a hierarchical Bayesian model with user clustering, domain-level confounders, and do-calculus-based causal adjustment. The authors report experiments on XMRec and MovieLens with five base recommenders (CDL, DLRM, PerK, NCF, LightGCN), showing that PRL improves the base models in cold-start cross-domain settings and that the causal component provides further gains.
Significance. The core idea—enhancing arbitrary deep-learning recommenders by learning a probabilistic residual correction with user clusters and confounder adjustment—is appealing and potentially practical. The paper includes multi-dataset, multi-base-model experiments and an ablation, which are useful. However, the technical derivation contains several load-bearing errors: the stated KL divergence is incorrect, the update rules invert a singular matrix, and the causal adjustment formula is not a valid backdoor adjustment. These issues call into question whether the reported results could have been produced by the algorithm as described. The contribution is not yet established; the manuscript requires substantial revision before it can be considered for publication.
major comments (5)
- [Section 2.2, Eq. (17)] The expression labeled D_KL(q(v_j) || p(v_j|x_v_j,s_m)) is not the KL divergence between a Gaussian q(v_j)=N(μ_v, Λ_v^{-1}I) and the product-of-Gaussians prior. With the prior's precision (Λ_v+λ_v)I and mean (Λ_v f_v + λ_v W_v s_m)/(Λ_v+λ_v), the quadratic term should be (Λ_v+λ_v)/2 ||μ_v − μ_pog||^2, not −λ_v/2||μ_v−W_v s_m||^2 − Λ_v/2||μ_v−f_v(x_v)||^2. Since this term is part of the ELBO and drives the update rules, the learning objective is not correctly derived.
- [Section 2.3, Eqs. (25)–(27)] The update rules for W_u, W_v, and w_R contain (s_m s_m^T)^{-1}. For any g>1, s_m s_m^T is a rank-one matrix and is singular; Section 2.1 allows g≪h with no restriction g=1, and Section 2.4 suggests learning country embeddings, which violates the invertibility assumption. Moreover, Algorithm 1 updates these parameters inside the per-domain loop, but Eqs. (25)–(27) sum over all users/items, so each iteration overwrites the previous domain's update instead of accumulating evidence. The algorithm as printed cannot be executed for typical g.
- [Section 2.4, Eq. (28)] The proposed causal adjustment p(eR|do(u),do(v)) = Σ_{m=1}^M p(eR|u,v,s_m)p(s_m) is not a well-defined backdoor formula. The generative model defines s_m as a continuous vector with prior N(0,I), so summing over a discrete domain index is meaningless; a correct adjustment would integrate over the confounder distribution. The paper also does not verify that the backdoor criterion holds for the graph in Fig. 2—e.g., it does not exclude unobserved confounders between u_i, v_j, and eR. The causal debiasing claim is therefore unsupported.
- [Tables 2 and S2] The 'DLRM PRL w/o Causality' row in Table S2 (MovieLens) is numerically identical to the 'DLRM PRL w/o Causality' row in Table 3 (XMRec): 0.0232, 0.0026, 0.0039, 0.0014, 0.0014. This is almost certainly an error and undermines confidence in the MovieLens results. Additionally, in the first MovieLens split, PRL (Full) slightly degrades DLRM's NDCG@20 (0.2431 vs 0.2433) and MAP@20 (0.0284 vs 0.0285), which is inconsistent with the blanket claim that PRL improves base models. No standard deviations or significance tests are reported.
- [Section 3.3] The experimental evaluation compares PRL only with its own base recommenders and an ablated version. Since the paper's stated scope is cross-domain recommendation, it should compare against existing cross-domain recommendation methods (e.g., CoNet, DDTCDR, or domain-adaptation baselines). Without such comparisons, and without code/data, the claim of consistent cross-domain improvement is not established. The authors should also report statistical significance across multiple runs.
minor comments (5)
- [Section 2.1] The notation f_x(·) appears in Algorithm 1 and Section 2.3('4)') but is not defined; the text uses f_v(·) for the item encoder. Please clarify.
- [Section 2.2, Eq. (10)] The term E_q(π)[p(π|θ)] is missing a log; in the standard ELBO it should be E_q(π)[log p(π|θ)]. This appears to be a typo but should be corrected.
- [Eq. (22)] The notation V λ_{eR(i,:)} V^T is ambiguous: λ_{eR(i,:)} is defined as a diagonal matrix over J items, but a user may have rated only a subset. The authors should specify how missing entries are handled (e.g., zero-padding or masking).
- [Table S11] The final row contains '.0002' instead of '0.0002', a minor formatting error.
- [General] The paper alternates between 'eR' and 'e_R' for the residual rating; please use a consistent notation throughout.
Circularity Check
No significant circularity: the residual target is defined independently of the base predictor, and the causal adjustment is a standard formula evaluated on held-out data.
full rationale
PRL's derivation chain is not circular. The residual is defined as eR_ij = R_ij - bR_ij with bR fixed (Sec. 2.1), so the final prediction R = bR + eR is an additive correction. Learning eR from observed residuals and evaluating on held-out cold-start users/domains (Tables 1-3, Fig. 4) is a genuine out-of-sample empirical claim, not a tautology: a residual model could in principle hurt performance. Equation 28 is the standard backdoor adjustment for the graph in Fig. 2, p(eR|do(u),do(v)) = sum_m p(eR|u,v,s_m)p(s_m); it is not fitted from the data and is compared against PRL w/o Causality on held-out metrics. The self-cited VDI [40] is used only as an estimator for the confounder embedding and is an externally published method, while the product-of-Gaussians identity is cited to Gales & Airey [5]; neither is a self-citation used to forbid alternatives. Two soundness concerns are worth noting but are not circularity: Eq. 25-27 use (s_m s_m^T)^{-1}, which is undefined for g>1 and suggests the printed update rules are not directly executable, and the backdoor/identifiability condition for s_m is assumed rather than proven. These affect correctness/verifiability, not whether the prediction reduces by construction to its inputs.
Assumptions & free parameters
free parameters (6)
- Cluster parameters {μ_k, Σ_k} =
K=3, values learned from data (Eq. 20-21)
- W_u, W_v, w_R =
learned via Eq. 25-27
- Domain confounder s_m =
estimated via VDI [40]
- K (number of user clusters) =
K=3 in all experiments
- Precision constants λ_eR, λ_v, Λ_v, λ_u, Λ_u =
not specified
- Encoder f_v parameters =
trained via gradient ascent
assumptions (4)
- domain assumption The generative SCM in Fig. 2: domain-level confounder s_m affects user latent u_i and item latent v_j, and residual rating eR depends on u_i, v_j, and s_m.
- domain assumption Backdoor criterion holds for Eq. 28: conditioning on s_m blocks all confounding paths between (u_i, v_j) and eR.
- standard math Product-of-Gaussians prior and mean-field variational factorization (Eq. 7-9) are used.
- domain assumption VDI [40] provides a valid posterior approximation p(s_m | eR, x_v, clusters).
invented entities (1)
-
Domain-level causal confounder s_m
Cite this review
Pith. "Pith review of Probabilistic Residual Learning for Online Recommendations." pith.science (2026). https://pith.science/paper/V5HIYYNX
@misc{pith2026260720863,
author = {Pith},
title = {Pith review of: Probabilistic Residual Learning for Online Recommendations},
year = {2026},
howpublished = {\url{https://pith.science/paper/V5HIYYNX}},
note = {Machine review of arXiv:2607.20863}
}
read the original abstract
Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffer from the black-box nature and computational complexity of the underlying models, making it difficult to systematically enhance their recommendation capabilities. To address this problem, we propose Probabilistic Residual Learning (PRL), a causal Bayesian recommendation model that models the residual between ground-truth and base predictions, enabling targeted refinement of existing systems. Specifically, PRL (1) probabilistically groups users for localized residual modeling, (2) models domain-level confounders that influence user and item representations, and (3) aggregates cluster-specific residual predictions over the confounders using do-calculus. Experiments demonstrate that our plug-and-play PRL is compatible with various base deep learning recommender systems, improving their performance while automatically discovering meaningful user clusters.
Figures
Figures from the paper (3 more)
Reference graph
Works this paper leans on
-
[1]
Michael Downes and Barbara Beeton , organization =. The
-
[2]
Cristophe Fiorio , year = 2015, month = oct, note =
2015
-
[3]
The algorithms bundle , author =
-
[4]
The Listings Package , author =
-
[5]
Publication quality tables in
Simon Fear , year = 2005, month = apr, note =. Publication quality tables in
2005
-
[6]
The subcaption package , author =
-
[7]
A package to create a nomenclature , author =
-
[8]
User Manual for glossaries.sty v4.44 , author =
Show all 155 references
-
[9]
David Carlisle , month = oct, year = 2004, note =. The
2004
-
[10]
TKDE , year=
Domain adaptation on graphs by learning aligned graph bases , author=. TKDE , year=
-
[11]
CVPR , pages=
Adagraph: Unifying predictive and continuous domain adaptation through graphs , author=. CVPR , pages=
-
[12]
KDD , pages=
Collaborative knowledge base embedding for recommender systems , author=. KDD , pages=. 2016 , organization=
2016
-
[13]
ECCV , volume =
Zhengming Ding and Sheng Li and Ming Shao and Yun Fu , title =. ECCV , volume =
-
[14]
Joty and Muhammad Imran , editor =
Firoj Alam and Shafiq R. Joty and Muhammad Imran , editor =. Domain Adaptation with Adversarial Training and Graph Embeddings , booktitle =
-
[15]
SIU , pages=
Domain Adaptation on Graphs via Frequency Analysis , author=. SIU , pages=
-
[16]
arXiv preprint arXiv:2004.10240 , year=
Neural forecasting: Introduction and literature overview , author=. arXiv preprint arXiv:2004.10240 , year=
2004 arXiv
-
[17]
arXiv preprint arXiv:1906.05264 , year=
Gluonts: Probabilistic time series models in python , author=. arXiv preprint arXiv:1906.05264 , year=
1906 arXiv
-
[18]
ICML , year=
Continuously Indexed Domain Adaptation , author=. ICML , year=
-
[19]
RecSys , pages=
Deep neural networks for youtube recommendations , author=. RecSys , pages=
-
[20]
NIPS , pages=
Deep learning for precipitation nowcasting: A benchmark and a new model , author=. NIPS , pages=
-
[21]
Convolutional
Shi, Xingjian and Chen, Zhourong and Wang, Hao and Yeung, Dit-Yan and Wong, Wai-Kin and Woo, Wang-chun , booktitle=. Convolutional
-
[22]
KDD , pages=
Collaborative variational autoencoder for recommender systems , author=. KDD , pages=
-
[23]
NIPS , pages=
Collaborative recurrent autoencoder: Recommend while learning to fill in the blanks , author=. NIPS , pages=
-
[24]
TDKE , volume=
Towards Bayesian deep learning: A framework and some existing methods , author=. TDKE , volume=
-
[25]
CSUR , volume=
A Survey on Bayesian Deep Learning , author=. CSUR , volume=
-
[26]
AAAI StarAI Workshop , year=
Causal discovery from incomplete data: A deep learning approach , author=. AAAI StarAI Workshop , year=
-
[27]
Frontiers in genetics , volume=
Review of causal discovery methods based on graphical models , author=. Frontiers in genetics , volume=. 2019 , publisher=
2019
-
[28]
ICML , year =
Jingquan Yan and Hao Wang , title =. ICML , year =
-
[29]
arXiv preprint arXiv:2203.11014 , year=
DHEN: A deep and hierarchical ensemble network for large-scale click-through rate prediction , author=. arXiv preprint arXiv:2203.11014 , year=
-
[30]
2017 , school=
Bayesian Deep Learning for Integrated Intelligence: Bridging the Gap between Perception and Inference , author=. 2017 , school=
2017
-
[31]
2022 , booktitle=
OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks , author=. 2022 , booktitle=
2022
-
[32]
Nature medicine , year=
Assessment of Medication Self-Administration using Artificial Intelligence , author=. Nature medicine , year=
-
[33]
Nature medicine , volume=
Artificial intelligence-enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals , author=. Nature medicine , volume=. 2022 , publisher=
2022
-
[34]
arXiv preprint arXiv:1111.0352 , year=
Revisiting k-means: New algorithms via Bayesian nonparametrics , author=. arXiv preprint arXiv:1111.0352 , year=
-
[35]
arXiv preprint arXiv:1906.00091 , year=
Deep learning recommendation model for personalization and recommendation systems , author=. arXiv preprint arXiv:1906.00091 , year=
1906 arXiv
-
[36]
Acm transactions on interactive intelligent systems (tiis) , volume=
The movielens datasets: History and context , author=. Acm transactions on interactive intelligent systems (tiis) , volume=. 2015 , publisher=
2015
-
[37]
Proceedings of the 26th international conference on world wide web , pages=
Neural collaborative filtering , author=. Proceedings of the 26th international conference on world wide web , pages=
-
[38]
Computer Speech & Language , volume=
Product of Gaussians for speech recognition , author=. Computer Speech & Language , volume=. 2006 , publisher=
2006
-
[39]
Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval , pages=
Lightgcn: Simplifying and powering graph convolution network for recommendation , author=. Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval , pages=
-
[40]
Relational stacked denoising autoencoder for tag recommendation , booktitle =
Hao Wang and Xingjian Shi and Dit. Relational stacked denoising autoencoder for tag recommendation , booktitle =
-
[41]
TKDE , volume=
Relational collaborative topic regression for recommender systems , author=. TKDE , volume=
-
[42]
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining , pages=
Collaborative topic modeling for recommending scientific articles , author=. Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining , pages=
-
[43]
Proceedings of the 30th ACM International Conference on Information & Knowledge Management , pages=
Cross-market product recommendation , author=. Proceedings of the 30th ACM International Conference on Information & Knowledge Management , pages=
-
[44]
IJCAI , pages =
Collaborative topic regression with social regularization for tag recommendation , author=. IJCAI , pages =
-
[45]
Bell and Chris Volinsky , title =
Yehuda Koren and Robert M. Bell and Chris Volinsky , title =. IEEE Computer , volume =. 2009 , pages =
2009
-
[46]
Session-based Recommendations with Recurrent Neural Networks , booktitle =
Bal. Session-based Recommendations with Recurrent Neural Networks , booktitle =
-
[47]
KDD , year =
Yifei Ma and Murali Balakrishnan Narayanaswamy and Haibin Lin and Hao Ding , title =. KDD , year =
-
[48]
Zico Kolter and Vladlen Koltun , title =
Shaojie Bai and J. Zico Kolter and Vladlen Koltun , title =. CoRR , volume =
-
[49]
Proceedings of the VLDB Endowment , volume=
Probabilistic demand forecasting at scale , author=. Proceedings of the VLDB Endowment , volume=. 2017 , publisher=
2017
-
[50]
NIPS , pages=
Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting , author=. NIPS , pages=
-
[51]
Maddix and Jan Gasthaus and Dean Foster and Tim Januschowski , title =
Yuyang Wang and Alex Smola and Danielle C. Maddix and Jan Gasthaus and Dean Foster and Tim Januschowski , title =. ICML , pages =
-
[52]
CoRR , volume =
Valentin Flunkert and David Salinas and Jan Gasthaus , title =. CoRR , volume =
-
[53]
IEEE transactions on power systems , volume=
ARIMA models to predict next-day electricity prices , author=. IEEE transactions on power systems , volume=. 2003 , publisher=
2003
-
[54]
international conference on machine learning , pages=
Dropout as a bayesian approximation: Representing model uncertainty in deep learning , author=. international conference on machine learning , pages=
-
[55]
Advances in neural information processing systems , pages=
Spatial transformer networks , author=. Advances in neural information processing systems , pages=
-
[56]
Natural-Parameter Networks:
Hao Wang and Xingjian Shi and Dit. Natural-Parameter Networks:. NIPS , pages =
-
[57]
arXiv preprint arXiv:1312.6114 , year=
Auto-encoding variational bayes , author=. arXiv preprint arXiv:1312.6114 , year=
-
[58]
2013 , publisher=
The skew-normal and related families , author=. 2013 , publisher=
2013
-
[59]
Kingma and Jimmy Ba , title =
Diederik P. Kingma and Jimmy Ba , title =. ICLR , year =
-
[60]
Xudong Mao and Qing Li and Haoran Xie and Raymond Y. K. Lau and Zhen Wang and Stephen Paul Smolley , title =. ICCV , pages =
-
[61]
Gordon , title =
Han Zhao and Remi Tachet des Combes and Kun Zhang and Geoffrey J. Gordon , title =. ICML , pages =
-
[62]
VLDB , volume=
Detecting change in data streams , author=. VLDB , volume=
-
[63]
AAAI , pages =
Seiichi Kuroki and Nontawat Charoenphakdee and Han Bao and Junya Honda and Issei Sato and Masashi Sugiyama , title =. AAAI , pages =
-
[64]
Adversarial Multiple Source Domain Adaptation , booktitle =
Han Zhao and Shanghang Zhang and Guanhang Wu and Jos. Adversarial Multiple Source Domain Adaptation , booktitle =
-
[65]
Castillo and Rama Chellappa , title =
Swami Sankaranarayanan and Yogesh Balaji and Carlos D. Castillo and Rama Chellappa , title =. CVPR , pages =
-
[66]
CVPR , pages =
Kuniaki Saito and Kohei Watanabe and Yoshitaka Ushiku and Tatsuya Harada , title =. CVPR , pages =
-
[67]
Jordan , title =
Mingsheng Long and Zhangjie Cao and Jianmin Wang and Michael I. Jordan , title =. NIPS , pages =
-
[68]
TKDE , volume=
A survey on transfer learning , author=. TKDE , volume=
-
[69]
JAMA , volume=
The National Sleep Research Resource: towards a sleep data commons , author=. JAMA , volume=
-
[70]
JAMA , volume=
Appendicular bone density and age predict hip fracture in women , author=. JAMA , volume=
-
[71]
Sleep , volume=
The sleep heart health study: design, rationale, and methods , author=. Sleep , volume=
-
[72]
NIPS , pages=
PyTorch: An imperative style, high-performance deep learning library , author=. NIPS , pages=
-
[73]
1994 , publisher=
Mixture density networks , author=. 1994 , publisher=
1994
-
[74]
NIPS , pages=
Generative adversarial nets , author=. NIPS , pages=
-
[75]
Jaakkola and Matt T
Mingmin Zhao and Shichao Yue and Dina Katabi and Tommi S. Jaakkola and Matt T. Bianchi , title =. ICML , pages =
-
[76]
ICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV) , pages =
Baochen Sun and Kate Saenko , title =. ICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV) , pages =
-
[77]
Machine learning , volume=
A theory of learning from different domains , author=. Machine learning , volume=
-
[78]
TNN , volume=
Domain adaptation via transfer component analysis , author=. TNN , volume=
-
[79]
arXiv preprint arXiv:1412.3474 , year=
Deep domain confusion: Maximizing for domain invariance , author=. arXiv preprint arXiv:1412.3474 , year=
-
[80]
CVPR , pages=
Maximum classifier discrepancy for unsupervised domain adaptation , author=. CVPR , pages=
-
[81]
arXiv preprint arXiv:1904.05801 , year=
Bridging theory and algorithm for domain adaptation , author=. arXiv preprint arXiv:1904.05801 , year=
1904 arXiv
-
[82]
arXiv preprint arXiv:1811.12751 , year=
Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption , author=. arXiv preprint arXiv:1811.12751 , year=
-
[83]
arXiv preprint arXiv:1702.05374 , year=
Domain adaptation for visual applications: A comprehensive survey , author=. arXiv preprint arXiv:1702.05374 , year=
-
[84]
CVPR , pages=
Adversarial discriminative domain adaptation , author=. CVPR , pages=
-
[85]
JMLR , volume=
Domain-adversarial training of neural networks , author=. JMLR , volume=. 2016 , publisher=
2016
-
[86]
NIPS , pages=
Coupled generative adversarial networks , author=. NIPS , pages=
-
[87]
CVPR , pages=
Generate to adapt: Aligning domains using generative adversarial networks , author=. CVPR , pages=
-
[88]
KDD , pages=
Learning Dynamics of Decision Boundaries without Additional Labeled Data , author=. KDD , pages=
-
[89]
CVPR , pages=
Continuous manifold based adaptation for evolving visual domains , author=. CVPR , pages=
-
[90]
Adapting to Continuously Shifting Domains , author=
-
[91]
arXiv preprint arXiv:1909.11448 , year=
CDOT: Continuous Domain Adaptation using Optimal Transport , author=. arXiv preprint arXiv:1909.11448 , year=
1909 arXiv
-
[92]
ICRA , pages=
Incremental adversarial domain adaptation for continually changing environments , author=. ICRA , pages=
-
[93]
TKDE , volume=
Incremental evolving domain adaptation , author=. TKDE , volume=
-
[94]
arXiv preprint arXiv:1812.01281 , year=
Towards Continuous Domain adaptation for Healthcare , author=. arXiv preprint arXiv:1812.01281 , year=
-
[95]
Geophysical Research Letters , number =
Grapenthin, Ronni and Freymueller, Jeffrey T , doi =. Geophysical Research Letters , number =
-
[96]
Computers & Geosciences , keywords =
Grapenthin, R , doi =. Computers & Geosciences , keywords =
-
[97]
Geophysical Research Letters , number =
Grapenthin, Ronni and Sigmundsson, Freysteinn and Geirsson, Halld\'. Geophysical Research Letters , number =. doi:L24305 Artn l24305 , isbn =
-
[98]
2018 IEEE international conference on data mining (ICDM) , pages=
Self-attentive sequential recommendation , author=. 2018 IEEE international conference on data mining (ICDM) , pages=. 2018 , organization=
2018
-
[99]
I (Still) Can't Believe It's Not Better! NeurIPS 2021 Workshop , year=
Language Models as Recommender Systems: Evaluations and Limitations , author=. I (Still) Can't Believe It's Not Better! NeurIPS 2021 Workshop , year=
2021
-
[100]
Proceedings of the 17th ACM Conference on Recommender Systems , pages=
Trending Now: Modeling Trend Recommendations , author=. Proceedings of the 17th ACM Conference on Recommender Systems , pages=
-
[101]
2023 , url =
Ziwei Fan and Hao Ding and Anoop Deoras and Trong Nghia Hoang , title =. 2023 , url =
2023
-
[102]
Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining , pages=
Collaborative deep learning for recommender systems , author=. Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining , pages=
-
[103]
SIGIR , pages =
Ziwei Zhu and Shahin Sefati and Parsa Saadatpanah and James Caverlee , title =. SIGIR , pages =
-
[104]
Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=
A Heterogeneous Graph Neural Model for Cold-Start Recommendation , author=. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=
-
[105]
Proceedings of the AAAI Conference on Artificial Intelligence , volume=
From zero-shot learning to cold-start recommendation , author=. Proceedings of the AAAI Conference on Artificial Intelligence , volume=
-
[106]
Yu , title =
Tingting Liang and Congying Xia and Yuyu Yin and Philip S. Yu , title =. SIGIR , pages =
-
[107]
SIGIR , pages =
Casper Hansen and Christian Hansen and Jakob Grue Simonsen and Stephen Alstrup and Christina Lioma , title =. SIGIR , pages =
-
[108]
KDD , pages =
Manqing Dong and Feng Yuan and Lina Yao and Xiwei Xu and Liming Zhu , title =. KDD , pages =
-
[109]
SIGIR , pages =
Ye Bi and Liqiang Song and Mengqiu Yao and Zhenyu Wu and Jianming Wang and Jing Xiao , title =. SIGIR , pages =
-
[110]
SIGIR , pages =
Le Wu and Yonghui Yang and Lei Chen and Defu Lian and Richang Hong and Meng Wang , title =. SIGIR , pages =
-
[111]
SIGIR , pages =
Fajie Yuan and Xiangnan He and Alexandros Karatzoglou and Liguang Zhang , title =. SIGIR , pages =
-
[112]
Proceedings of the AAAI conference on artificial intelligence , volume=
Session-based recommendation with graph neural networks , author=. Proceedings of the AAAI conference on artificial intelligence , volume=
-
[113]
arXiv preprint arXiv:1205.2618 , year=
BPR: Bayesian personalized ranking from implicit feedback , author=. arXiv preprint arXiv:1205.2618 , year=
-
[114]
Proceedings of the 10th ACM conference on recommender systems , pages=
Are you influenced by others when rating? Improve rating prediction by conformity modeling , author=. Proceedings of the 10th ACM conference on recommender systems , pages=
-
[115]
Advances in neural information processing systems , volume=
Language models are few-shot learners , author=. Advances in neural information processing systems , volume=
-
[116]
arXiv preprint arXiv:2205.01068 , year=
Opt: Open pre-trained transformer language models , author=. arXiv preprint arXiv:2205.01068 , year=
-
[117]
arXiv preprint arXiv:1810.04805 , year=
Bert: Pre-training of deep bidirectional transformers for language understanding , author=. arXiv preprint arXiv:1810.04805 , year=
-
[118]
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, Nils and Gurevych, Iryna. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. 2019
2019
-
[119]
ICML , year =
Tianyi Liu and Zihao Xu and Hao He and Guangyuan Hao and Guang-He Lee and Hao Wang , title =. ICML , year =
-
[120]
ICLR , year=
Graph-Relational Domain Adaptation , author=. ICLR , year=
-
[121]
ICLR , year =
Zihao Xu and Guangyuan Hao and Hao He and Hao Wang , title =. ICLR , year =
-
[122]
Proceedings of the ACM on Web Conference 2024 , pages=
Top-Personalized-K Recommendation , author=. Proceedings of the ACM on Web Conference 2024 , pages=
2024
-
[123]
NeurIPS , year =
Haizhou Shi and Hao Wang , title =. NeurIPS , year =
-
[124]
Advances in neural information processing systems , volume=
Probabilistic matrix factorization , author=. Advances in neural information processing systems , volume=
-
[125]
arXiv preprint arXiv:2105.08318 , year=
Zero-shot recommender systems , author=. arXiv preprint arXiv:2105.08318 , year=
-
[126]
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=
Causal intervention for leveraging popularity bias in recommendation , author=. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=
-
[127]
Proceedings of the Web Conference 2021 , pages=
Disentangling user interest and conformity for recommendation with causal embedding , author=. Proceedings of the Web Conference 2021 , pages=
2021
-
[128]
Acm Sigir Forum , volume=
Accurately interpreting clickthrough data as implicit feedback , author=. Acm Sigir Forum , volume=. 2017 , organization=
2017
-
[129]
2009 , publisher=
Causality , author=. 2009 , publisher=
2009
-
[130]
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages=
Temporal-contextual recommendation in real-time , author=. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages=
-
[131]
Causal Intervention for Leveraging Popularity Bias in Recommendation , booktitle =
Yang Zhang and Fuli Feng and Xiangnan He and Tianxin Wei and Chonggang Song and Guohui Ling and Yongdong Zhang , editor =. Causal Intervention for Leveraging Popularity Bias in Recommendation , booktitle =. 2021 , url =. doi:10.1145/3404835.3462875 , timestamp =
2021
-
[132]
Temporal-Contextual Recommendation in Real-Time , booktitle =
Yifei Ma and Balakrishnan (Murali) Narayanaswamy and Haibin Lin and Hao Ding , editor =. Temporal-Contextual Recommendation in Real-Time , booktitle =. 2020 , url =. doi:10.1145/3394486.3403278 , timestamp =
2020
-
[133]
Towards Universal Sequence Representation Learning for Recommender Systems , journal =
Yupeng Hou and Shanlei Mu and Wayne Xin Zhao and Yaliang Li and Bolin Ding and Ji. Towards Universal Sequence Representation Learning for Recommender Systems , journal =. 2022 , url =. doi:10.48550/arXiv.2206.05941 , eprinttype =. 2206.05941 , timestamp =
-
[134]
arXiv preprint arXiv:1511.06939 , year=
Session-based recommendations with recurrent neural networks , author=. arXiv preprint arXiv:1511.06939 , year=
-
[135]
Kingma and Jimmy Ba , editor =
Diederik P. Kingma and Jimmy Ba , editor =. Adam:. 3rd International Conference on Learning Representations,. 2015 , url =
2015
-
[136]
CoRR , volume =
Yu Zheng and Chen Gao and Xiang Li and Xiangnan He and Yong Li and Depeng Jin , title =. CoRR , volume =. 2020 , url =. 2006.11011 , timestamp =
2020 arXiv
-
[137]
Cross-Domain Recommendation: Challenges, Progress, and Prospects , booktitle =
Feng Zhu and Yan Wang and Chaochao Chen and Jun Zhou and Longfei Li and Guanfeng Liu , editor =. Cross-Domain Recommendation: Challenges, Progress, and Prospects , booktitle =. 2021 , url =. doi:10.24963/ijcai.2021/639 , timestamp =
2021 doi
-
[138]
2020 , url =
Pan Li and Alexander Tuzhilin , editor =. 2020 , url =. doi:10.1145/3336191.3371793 , timestamp =
2020
-
[139]
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , journal =
Junyoung Chung and. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , journal =. 2014 , url =. 1412.3555 , timestamp =
2014 arXiv
-
[140]
Advances in neural information processing systems , volume=
Attention is all you need , author=. Advances in neural information processing systems , volume=
-
[141]
IEEE transactions on neural networks , volume=
The graph neural network model , author=. IEEE transactions on neural networks , volume=. 2008 , publisher=
2008
-
[142]
Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining , pages=
Kgat: Knowledge graph attention network for recommendation , author=. Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining , pages=
-
[143]
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining , pages=
Debiasing learning based cross-domain recommendation , author=. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining , pages=
-
[144]
Proceedings of the 27th
Guangneng Hu and Yu Zhang and Qiang Yang , title =. Proceedings of the 27th
-
[145]
Proceedings of the 28th
Cheng Zhao and Chenliang Li and Cong Fu , title =. Proceedings of the 28th
-
[146]
Meng Liu and Jianjun Li and Guohui Li and Peng Pan , title =
-
[147]
Debiasing Learning based Cross-domain Recommendation , booktitle =
Siqing Li and Liuyi Yao and Shanlei Mu and Wayne Xin Zhao and Yaliang Li and Tonglei Guo and Bolin Ding and Ji. Debiasing Learning based Cross-domain Recommendation , booktitle =
-
[148]
Xiaoyu Du and Zike Wu and Fuli Feng and Xiangnan He and Jinhui Tang , title =
-
[149]
Yu and Peng Cui , title =
Zimu Wang and Yue He and Jiashuo Liu and Wenchao Zou and Philip S. Yu and Peng Cui , title =
- [150]
-
[151]
RecSys '22: Sixteenth
Shijie Geng and Shuchang Liu and Zuohui Fu and Yingqiang Ge and Yongfeng Zhang , title =. RecSys '22: Sixteenth
-
[152]
ACM Transactions on Information Systems , volume=
Bias and debias in recommender system: A survey and future directions , author=. ACM Transactions on Information Systems , volume=. 2023 , publisher=
2023
-
[153]
Proceedings of the 14th ACM Conference on Recommender Systems , pages=
Causal inference for recommender systems , author=. Proceedings of the 14th ACM Conference on Recommender Systems , pages=
-
[154]
Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining , pages=
Towards universal sequence representation learning for recommender systems , author=. Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining , pages=
-
[155]
Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval , pages=
Causerec: Counterfactual user sequence synthesis for sequential recommendation , author=. Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval , pages=
Reviewed August 1, 2026 · model on record in the stance chip above.
Discussion (0). Sign in to comment.