# Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation

arXiv: https://arxiv.org/abs/2112.08679 · HTML: https://mlsanity.com/paper/2112.08679/

## Key facts

- Cited by 173 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2021.

## Built on by (most cited first, 30 of 173)

- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2302.08191/) (2023)
- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [On Softmax Direct Preference Optimization for Recommendation](https://mlsanity.com/paper/2406.09215/) (2024)
- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [Hyperbolic Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/2202.13852/) (2022)
- [COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning](https://mlsanity.com/paper/2206.04726/) (2022)
- [Multimodal Recommender Systems: A Survey](https://mlsanity.com/paper/2302.03883/) (2023)
- [Linear-Time Graph Neural Networks for Scalable Recommendations](https://mlsanity.com/paper/2402.13973/) (2024)
- [Heterogeneous Contrastive Learning for Foundation Models and Beyond](https://mlsanity.com/paper/2404.00225/) (2024)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [Knowledge Graph Self-Supervised Rationalization for Recommendation](https://mlsanity.com/paper/2307.02759/) (2023)
- [Rethinking Graph Masked Autoencoders through Alignment and Uniformity](https://mlsanity.com/paper/2402.07225/) (2024)
- [RDRec: Rationale Distillation for LLM-based Recommendation](https://mlsanity.com/paper/2405.10587/) (2024)
- [Graph Self-supervised Learning with Accurate Discrepancy Learning](https://mlsanity.com/paper/2202.02989/) (2022)
- [How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective](https://mlsanity.com/paper/2404.12008/) (2024)
- [Efficient Bi-Level Optimization for Recommendation Denoising](https://mlsanity.com/paper/2210.10321/) (2022)
- [Adap-τ: Adaptively Modulating Embedding Magnitude for Recommendation](https://mlsanity.com/paper/2302.04775/) (2023)
- [ContextGNN: Beyond Two-Tower Recommendation Systems](https://mlsanity.com/paper/2411.19513/) (2024)
- [FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction](https://mlsanity.com/paper/2405.17898/) (2024)
- [Language Representations Can be What Recommenders Need: Findings and Potentials](https://mlsanity.com/paper/2407.05441/) (2024)
- [MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation](https://mlsanity.com/paper/2412.08847/) (2024)
- [SSLRec: A Self-Supervised Learning Framework for Recommendation](https://mlsanity.com/paper/2308.05697/) (2023)
- [GraphPro: Graph Pre-training and Prompt Learning for Recommendation](https://mlsanity.com/paper/2311.16716/) (2023)
- [Graph Sparsification via Mixture of Graphs](https://mlsanity.com/paper/2405.14260/) (2024)
- [Graph Soft-Contrastive Learning via Neighborhood Ranking](https://mlsanity.com/paper/2209.13964/) (2022)
- [PyG-SSL: A Graph Self-Supervised Learning Toolkit](https://mlsanity.com/paper/2412.21151/) (2024)
- [STERLING: Synergistic Representation Learning on Bipartite Graphs](https://mlsanity.com/paper/2302.05428/) (2023)

## Abstract (arXiv)

Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data sparsity issue. A typical pipeline of CL-based recommendation models is first augmenting the user-item bipartite graph with structure perturbations, and then maximizing the node representation consistency between different graph augmentations. Although this paradigm turns out to be effective, what underlies the performance gains is still a mystery. In this paper, we first experimentally disclose that, in CL-based recommendation models, CL operates by learning more evenly distributed user/item representations that can implicitly mitigate the popularity bias. Meanwhile, we reveal that the graph augmentations, which were considered necessary, just play a trivial role. Based on this finding, we propose a simple CL method which discards the graph augmentations and instead adds uniform noises to the embedding space for creating contrastive views. A comprehensive experimental study on three benchmark datasets demonstrates that, though it appears strikingly simple, the proposed method can smoothly adjust the uniformity of learned representations and has distinct advantages over its graph augmentation-based counterparts in terms of recommendation accuracy and training efficiency. The code is released at https://github.com/Coder-Yu/QRec.