# Self-supervised Graph Learning for Recommendation

arXiv: https://arxiv.org/abs/2010.10783 · HTML: https://mlsanity.com/paper/2010.10783/

## Key facts

- Cited by 305 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 30 of 305)

- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Intent Contrastive Learning for Sequential Recommendation](https://mlsanity.com/paper/2202.02519/) (2022)
- [Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning](https://mlsanity.com/paper/2202.06200/) (2022)
- [OpenGraph: Towards Open Graph Foundation Models](https://mlsanity.com/paper/2403.01121/) (2024)
- [LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2302.08191/) (2023)
- [Knowledge Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2205.00976/) (2022)
- [SimpleX: A Simple and Strong Baseline for Collaborative Filtering](https://mlsanity.com/paper/2109.12613/) (2021)
- [On Softmax Direct Preference Optimization for Recommendation](https://mlsanity.com/paper/2406.09215/) (2024)
- [Hypergraph Contrastive Collaborative Filtering](https://mlsanity.com/paper/2204.12200/) (2022)
- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [GIF: A General Graph Unlearning Strategy via Influence Function](https://mlsanity.com/paper/2304.02835/) (2023)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [Contrastive Self-supervised Sequential Recommendation with Robust Augmentation](https://mlsanity.com/paper/2108.06479/) (2021)
- [LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning](https://mlsanity.com/paper/2503.04812/) (2025)
- [Graph Trend Filtering Networks for Recommendations](https://mlsanity.com/paper/2108.05552/) (2021)
- [Zero-Shot Next-Item Recommendation using Large Pretrained Language Models](https://mlsanity.com/paper/2304.03153/) (2023)
- [AnyGraph: Graph Foundation Model in the Wild](https://mlsanity.com/paper/2408.10700/) (2024)
- [DiffKG: Knowledge Graph Diffusion Model for Recommendation](https://mlsanity.com/paper/2312.16890/) (2023)
- [COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning](https://mlsanity.com/paper/2206.04726/) (2022)
- [Contrastive Meta Learning with Behavior Multiplicity for Recommendation](https://mlsanity.com/paper/2202.08523/) (2022)
- [Blurring-Sharpening Process Models for Collaborative Filtering](https://mlsanity.com/paper/2211.09324/) (2022)
- [Self-Supervised Hypergraph Transformer for Recommender Systems](https://mlsanity.com/paper/2207.14338/) (2022)
- [Linear-Time Graph Neural Networks for Scalable Recommendations](https://mlsanity.com/paper/2402.13973/) (2024)
- [Denoising Diffusion Recommender Model](https://mlsanity.com/paper/2401.06982/) (2024)
- [Disentangled Contrastive Learning for Social Recommendation](https://mlsanity.com/paper/2208.08723/) (2022)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2304.01563/) (2023)
- [Disentangled Contrastive Collaborative Filtering](https://mlsanity.com/paper/2305.02759/) (2023)
- [Knowledge Graph Self-Supervised Rationalization for Recommendation](https://mlsanity.com/paper/2307.02759/) (2023)
- [DiffMM: Multi-Modal Diffusion Model for Recommendation](https://mlsanity.com/paper/2406.11781/) (2024)

## Abstract (arXiv)

Representation learning on user-item graph for recommendation has evolved from using single ID or interaction history to exploiting higher-order neighbors. This leads to the success of graph convolution networks (GCNs) for recommendation such as PinSage and LightGCN. Despite effectiveness, we argue that they suffer from two limitations: (1) high-degree nodes exert larger impact on the representation learning, deteriorating the recommendations of low-degree (long-tail) items; and (2) representations are vulnerable to noisy interactions, as the neighborhood aggregation scheme further enlarges the impact of observed edges. In this work, we explore self-supervised learning on user-item graph, so as to improve the accuracy and robustness of GCNs for recommendation. The idea is to supplement the classical supervised task of recommendation with an auxiliary self-supervised task, which reinforces node representation learning via self-discrimination. Specifically, we generate multiple views of a node, maximizing the agreement between different views of the same node compared to that of other nodes. We devise three operators to generate the views -- node dropout, edge dropout, and random walk -- that change the graph structure in different manners. We term this new learning paradigm as textitSelf-supervised Graph Learning (SGL), implementing it on the state-of-the-art model LightGCN. Through theoretical analyses, we find that SGL has the ability of automatically mining hard negatives. Empirical studies on three benchmark datasets demonstrate the effectiveness of SGL, which improves the recommendation accuracy, especially on long-tail items, and the robustness against interaction noises. Our implementations are available at urlhttps://github.com/wujcan/SGL.