Sharpness-Aware Graph Collaborative Filtering
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) have achieved impressive performance in collaborative filtering. However, GNNs tend to yield inferior performance when the distributions of training and test data are not aligned well. Also, training GNNs requires optimizing non-convex neural networks with an abundance of local and global minima, which may differ widely in their performance at test time. Thus, it is essential to choose the minima carefully. Here we propose an effective training schema, called gSAM, under the principle that the textitflatter minima has a better generalization ability than the textitsharper ones. To achieve this goal, gSAM regularizes the flatness of the weight loss landscape by forming a bi-level optimization: the outer problem conducts the standard model training while the inner problem helps the model jump out of the sharp minima. Experimental results show the superiority of our gSAM.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 18 Jul 2023.
Builds on
28 of 38 references.
References · 28
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
- 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
- 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
- 2019Neural Graph Collaborative Filteringcited by 660
- 2017Exploring Generalization in Deep Learningcited by 595
- 2019Fantastic Generalization Measures and Where to Find Themcited by 507
- 2017A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networkscited by 309
- 2020Self-supervised Graph Learning for Recommendationcited by 305
- 2019Optimizing Millions of Hyperparameters by Implicit Differentiationcited by 303
16 more
- 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
- 2016Deep Learning without Poor Local Minimacited by 233
- 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
- 2022Towards Understanding Sharpness-Aware Minimizationcited by 145
- 2022Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learningcited by 86
- 2020A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networkscited by 84
- 2022Fisher SAM: Information Geometry and Sharpness Aware Minimisationcited by 84
- 2018Reviving and Improving Recurrent Back-Propagationcited by 69
- 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
- 2020Streaming Graph Neural Networks via Continual Learningcited by 63
- 2021Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyondcited by 62
- 2022Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakagecited by 61
- 2019Bad Global Minima Exist and SGD Can Reach Themcited by 49
- 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 42
- 2022Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graphcited by 10
- 2022TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systemscited by 7
Built on by
Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.
3 papers.