Pith. sign in

REVIEW 12 cited by

Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.01034 v3 pith:GOTGUPBA submitted 2024-06-03 cs.IR

Jinfeng Xu , Zheyu Chen , Jinze Li , Shuo Yang , Wei Wang , Xiping Hu , Edith Ngai This is my paper · ORCID
classification cs.IR
keywords graphtransformationbackbonecollaborativefeaturefourierkan-gcfmodelsachieve
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph Collaborative Filtering (GCF) has emerged as a dominant paradigm in modern recommendation systems, excelling at modeling complex user-item interactions and capturing high-order collaborative signals through graph-structured learning. Most existing GCF models predominantly rely on simplified graph architectures like LightGCN, which strategically remove feature transformation and activation functions from vanilla graph convolution networks. Through systematic analysis, we reveal that feature transformation in message propagation can enhance model representation, though at the cost of increased training difficulty. To this end, we propose FourierKAN-GCF, a novel GCN framework that adopts Fourier Kolmogorov-Arnold Networks as efficient transformation modules within graph propagation layers. This design enhances model representation while decreasing training difficulty. Our FourierKAN-GCF can achieve higher recommendation performance than most widely used GCF backbone models. In addition, it can be integrated into existing advanced self-supervised models as a backbone, replacing their original backbone to achieve enhanced performance. Extensive experiments on three public datasets demonstrate the superiority of FourierKAN-GCF.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification

    cs.AI 2026-08 conditional novelty 6.0 of 10

    A primary-preserving retain-or-correct policy, trained from out-of-fold residual utility, improves modulation classification accuracy on RadioML and Hisar benchmarks by 1.0 to 2.7 percentage points.

  2. The Best is Yet to Come: Graph Convolution in the Testing Phase for Multimodal Recommendation

    cs.IR 2025-07 conditional novelty 6.0 of 10

    A multimodal recommender that trains without graph convolution and applies it only at test time outperforms graph-trained baselines while training much faster.

  3. NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation

    cs.IR 2025-07 conditional novelty 6.0 of 10

    NLGCL treats each user/item embedding and its graph neighbors at the next GNN layer as positive pairs, eliminating augmentation-based contrastive views in GNN recommenders while improving accuracy and training speed.

  4. Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Khan-GCL combines KAN encoders with coefficient-based critical feature identification to generate hard negatives and reports state-of-the-art graph classification results.

  5. Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks

    quant-ph 2025-09 reject novelty 5.0 of 10

    QKANs show strong empirical performance on regression, vision, and language tasks, but the claimed exponential parameter reduction is not rigorously established.

  6. Toroidal area-preserving parameterizations of genus-one closed surfaces

    math.NA 2025-08 unverdicted novelty 5.0 of 10

    Four Riemannian optimization algorithms (projected/Riemannian gradient and conjugate gradient) are proposed to compute toroidal area-preserving parameterizations by minimizing stretch energy on a power manifold of ring tori.

  7. Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks

    stat.ML 2025-08 reject novelty 5.0 of 10

    The paper states universal approximation theorems for sine-based Kolmogorov-Arnold networks, but the proof relies on an invalid lemma and an unproven matrix invertibility.

  8. MDVT: Enhancing Multimodal Recommendation with Model-Agnostic Multimodal-Driven Virtual Triplets

    cs.IR 2025-05 conditional novelty 5.0 of 10

    MDVT improves multimodal recommenders by training them on virtual positive/negative item pairs selected by embedding similarity after a warm-up phase.

  9. SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions

    cs.LG 2026-06 conditional novelty 4.0 of 10

    SechKAN combines sech basis functions with a 1D linear projection to build a KAN-style model whose parameter count matches MLPs and which is competitive or better than several KAN variants on tested benchmarks.

  10. Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Augmenting Kolmogorov-Arnold Networks with prediction exits at each layer improves accuracy and often yields more parsimonious models, and a differentiable learning-to-exit algorithm automates the choice of exit weights.

  11. Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment

    eess.IV 2025-05 conditional novelty 4.0 of 10

    A Taylor-expansion KAN variant outperforms B-spline, orthogonal-polynomial, wavelet, and Fourier KAN variants and MLPs on five authentic BIQA databases, with PCA and shallow layers reducing training cost.

  12. The modified Physics-Informed Hybrid Parallel Kolmogorov--Arnold and Multilayer Perceptron Architecture with domain decomposition

    math.NA 2025-11 conditional novelty 3.0 of 10

    A hybrid KAN-MLP physics-informed network with a trainable convex weight and overlapping domain decomposition improves reported accuracy on high-frequency and multiscale PDE benchmarks.

Pith tools