# Self-Guided Learning to Denoise for Robust Recommendation

arXiv: https://arxiv.org/abs/2204.06832 · HTML: https://mlsanity.com/paper/2204.06832/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2022.

## Built on by (most cited first, 24 of 24)

- [Denoising Diffusion Recommender Model](https://mlsanity.com/paper/2401.06982/) (2024)
- [Efficient Bi-Level Optimization for Recommendation Denoising](https://mlsanity.com/paper/2210.10321/) (2022)
- [Double Correction Framework for Denoising Recommendation](https://mlsanity.com/paper/2405.11272/) (2024)
- [Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising](https://mlsanity.com/paper/2508.05352/) (2025)
- [LLM4DSR: Leveraging Large Language Model for Denoising Sequential Recommendation](https://mlsanity.com/paper/2408.08208/) (2024)
- [PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation](https://mlsanity.com/paper/2305.16163/) (2023)
- [Debiased Recommendation with Noisy Feedback](https://mlsanity.com/paper/2406.17182/) (2024)
- [Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction](https://mlsanity.com/paper/2312.06682/) (2023)
- [Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis](https://mlsanity.com/paper/2308.00404/) (2023)
- [Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation](https://mlsanity.com/paper/2409.10343/) (2024)
- [Advancing Loss Functions in Recommender Systems: A Comparative Study with a R'enyi Divergence-Based Solution](https://mlsanity.com/paper/2506.15120/) (2025)
- [Label Denoising through Cross-Model Agreement](https://mlsanity.com/paper/2308.13976/) (2023)
- [When SparseMoE Meets Noisy Interactions: An Ensemble View on Denoising Recommendation](https://mlsanity.com/paper/2409.12730/) (2024)
- [DeBaTeR: Denoising Bipartite Temporal Graph for Recommendation](https://mlsanity.com/paper/2411.09181/) (2024)
- [S2DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion](https://mlsanity.com/paper/2412.15822/) (2024)
- [Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing](https://mlsanity.com/paper/2503.07823/) (2025)
- [From Entity Reliability to Clean Feedback: An Entity-Aware Denoising Framework Beyond Interaction-Level Signals](https://mlsanity.com/paper/2508.10851/) (2025)
- [Hard vs. Noise: Resolving Hard-Noisy Sample Confusion in Recommender Systems via Large Language Models](https://mlsanity.com/paper/2511.07295/) (2025)
- [TFPS: A Temporal Filtration-enhanced Positive Sample Set Construction Method for Implicit Collaborative Filtering](https://mlsanity.com/paper/2602.22521/) (2026)
- [AlphaFree: Recommendation Free from Users, IDs, and GNNs](https://mlsanity.com/paper/2603.02653/) (2026)
- [Joint Behavior-guided and Modality-coherence Conditional Graph Diffusion Denoising for Multi Modal Recommendation](https://mlsanity.com/paper/2604.03654/) (2026)
- [Learning Robust Recommenders from Noisy Implicit Feedback via GMM-Weighted Bayesian Transition Matrix](https://mlsanity.com/paper/2605.20721/) (2026)
- [ANCHOR: Agentic Noise Creation Framework for Human Simulation and Denoising Recommendation](https://mlsanity.com/paper/2606.05621/) (2026)
- [Denoising Implicit Feedback for Cold-start Recommendation](https://mlsanity.com/paper/2606.19658/) (2026)

## Abstract (arXiv)

The ubiquity of implicit feedback makes them the default choice to build modern recommender systems. Generally speaking, observed interactions are considered as positive samples, while unobserved interactions are considered as negative ones. However, implicit feedback is inherently noisy because of the ubiquitous presence of noisy-positive and noisy-negative interactions. Recently, some studies have noticed the importance of denoising implicit feedback for recommendations, and enhanced the robustness of recommendation models to some extent. Nonetheless, they typically fail to (1) capture the hard yet clean interactions for learning comprehensive user preference, and (2) provide a universal denoising solution that can be applied to various kinds of recommendation models. In this paper, we thoroughly investigate the memorization effect of recommendation models, and propose a new denoising paradigm, i.e., Self-Guided Denoising Learning (SGDL), which is able to collect memorized interactions at the early stage of the training (i.e., "noise-resistant" period), and leverage those data as denoising signals to guide the following training (i.e., "noise-sensitive" period) of the model in a meta-learning manner. Besides, our method can automatically switch its learning phase at the memorization point from memorization to self-guided learning, and select clean and informative memorized data via a novel adaptive denoising scheduler to improve the robustness. We incorporate SGDL with four representative recommendation models (i.e., NeuMF, CDAE, NGCF and LightGCN) and different loss functions (i.e., binary cross-entropy and BPR loss). The experimental results on three benchmark datasets demonstrate the effectiveness of SGDL over the state-of-the-art denoising methods like T-CE, IR, DeCA, and even state-of-the-art robust graph-based methods like SGCN and SGL.