Deoscillated Adaptive Graph Collaborative Filtering

Zhiwei Liu, Lin Meng, Fei Jiang, Jiawei Zhang, Philip S. Yu
Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, PMLR 196:248-257, 2022.

Abstract

Collaborative Filtering (CF) signals are crucial for a Recommender System (RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modeled through propagating the information over the user-item bipartite graph. Recent Graph Neural Networks (GNNs) propose to stack multiple aggregation layers to propagate high-order signals. However, there are three challenges, the oscillation problem, varying locality of bipartite graphs, and the fixed propagation pattern, which spoil the ability of the multi-layer structure to propagate information. In this paper, we theoretically prove the existence and boundary of the oscillation problem, and empirically study the varying locality and layer-fixed propagation problems. We propose a new RS model, named as Deoscillated adaptive Graph Collaborative Filtering (DGCF), which is constituted by stacking multiple CHP layers and LA layers. We conduct extensive experiments on real-world datasets to verify the effectiveness of DGCF. Detailed analyses indicate that DGCF solves oscillation problems, adaptively learns local factors, and has layer-wise propagation patterns.

Cite this Paper

BibTeX
@InProceedings{pmlr-v196-liu22b, title = {Deoscillated Adaptive Graph Collaborative Filtering}, author = {Liu, Zhiwei and Meng, Lin and Jiang, Fei and Zhang, Jiawei and Yu, Philip S.}, booktitle = {Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022}, pages = {248--257}, year = {2022}, editor = {Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Kaul, Manohar and Ktena, Ira and Kvinge, Henry and Miolane, Nina and Rieck, Bastian and Tymochko, Sarah and Wolf, Guy}, volume = {196}, series = {Proceedings of Machine Learning Research}, month = {25 Feb--22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v196/liu22b/liu22b.pdf}, url = {https://proceedings.mlr.press/v196/liu22b.html}, abstract = {Collaborative Filtering (CF) signals are crucial for a Recommender System (RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modeled through propagating the information over the user-item bipartite graph. Recent Graph Neural Networks (GNNs) propose to stack multiple aggregation layers to propagate high-order signals. However, there are three challenges, the oscillation problem, varying locality of bipartite graphs, and the fixed propagation pattern, which spoil the ability of the multi-layer structure to propagate information. In this paper, we theoretically prove the existence and boundary of the oscillation problem, and empirically study the varying locality and layer-fixed propagation problems. We propose a new RS model, named as Deoscillated adaptive Graph Collaborative Filtering (DGCF), which is constituted by stacking multiple CHP layers and LA layers. We conduct extensive experiments on real-world datasets to verify the effectiveness of DGCF. Detailed analyses indicate that DGCF solves oscillation problems, adaptively learns local factors, and has layer-wise propagation patterns. } }
Endnote
%0 Conference Paper %T Deoscillated Adaptive Graph Collaborative Filtering %A Zhiwei Liu %A Lin Meng %A Fei Jiang %A Jiawei Zhang %A Philip S. Yu %B Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022 %C Proceedings of Machine Learning Research %D 2022 %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Manohar Kaul %E Ira Ktena %E Henry Kvinge %E Nina Miolane %E Bastian Rieck %E Sarah Tymochko %E Guy Wolf %F pmlr-v196-liu22b %I PMLR %P 248--257 %U https://proceedings.mlr.press/v196/liu22b.html %V 196 %X Collaborative Filtering (CF) signals are crucial for a Recommender System (RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modeled through propagating the information over the user-item bipartite graph. Recent Graph Neural Networks (GNNs) propose to stack multiple aggregation layers to propagate high-order signals. However, there are three challenges, the oscillation problem, varying locality of bipartite graphs, and the fixed propagation pattern, which spoil the ability of the multi-layer structure to propagate information. In this paper, we theoretically prove the existence and boundary of the oscillation problem, and empirically study the varying locality and layer-fixed propagation problems. We propose a new RS model, named as Deoscillated adaptive Graph Collaborative Filtering (DGCF), which is constituted by stacking multiple CHP layers and LA layers. We conduct extensive experiments on real-world datasets to verify the effectiveness of DGCF. Detailed analyses indicate that DGCF solves oscillation problems, adaptively learns local factors, and has layer-wise propagation patterns.
APA
Liu, Z., Meng, L., Jiang, F., Zhang, J. & Yu, P.S.. (2022). Deoscillated Adaptive Graph Collaborative Filtering. Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, in Proceedings of Machine Learning Research 196:248-257 Available from https://proceedings.mlr.press/v196/liu22b.html.

Related Material