# A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation

arXiv: https://arxiv.org/abs/2508.19507 · HTML: https://mlsanity.com/paper/2508.19507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MoE for recommender systems, one of 12 directions in Mixture-of-experts.
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Placed in

- Mixture-of-experts / [MoE for recommender systems](https://mlsanity.com/moe/moe-for-recommender-systems/)

## Builds on (most cited first, 21 of 21)

- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions](https://mlsanity.com/paper/2109.12843/) (2021)
- [Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning](https://mlsanity.com/paper/2202.06200/) (2022)
- [LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2302.08191/) (2023)
- [Graph Meta Network for Multi-Behavior Recommendation](https://mlsanity.com/paper/2110.03969/) (2021)
- [Contrastive Meta Learning with Behavior Multiplicity for Recommendation](https://mlsanity.com/paper/2202.08523/) (2022)
- [Facial Expression Analysis under Partial Occlusion: A Survey](https://mlsanity.com/paper/1802.08784/) (2018)
- [Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network](https://mlsanity.com/paper/2110.04002/) (2021)
- [Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation](https://mlsanity.com/paper/2109.02859/) (2021)
- [Contrastive Collaborative Filtering for Cold-Start Item Recommendation](https://mlsanity.com/paper/2302.02151/) (2023)
- [Cascading Residual Graph Convolutional Network for Multi-Behavior Recommendation](https://mlsanity.com/paper/2205.13128/) (2022)
- [Multi-behavior Self-supervised Learning for Recommendation](https://mlsanity.com/paper/2305.18238/) (2023)
- [Multi-Behavior Recommendation with Cascading Graph Convolution Networks](https://mlsanity.com/paper/2303.15720/) (2023)
- [Parallel Knowledge Enhancement based Framework for Multi-behavior Recommendation](https://mlsanity.com/paper/2308.04807/) (2023)
- [Behavior-Contextualized Item Preference Modeling for Multi-Behavior Recommendation](https://mlsanity.com/paper/2404.18166/) (2024)
- [Achieving Human Parity on Visual Question Answering](https://mlsanity.com/paper/2111.08896/) (2021)
- [Multi-Behavior Recommender Systems: A Survey](https://mlsanity.com/paper/2503.06963/) (2025)
- [MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-behavior Recommendation](https://mlsanity.com/paper/2306.10679/) (2023)

## Abstract (arXiv)

In e-commerce, where users face a vast array of possible item choices, recommender systems are vital for helping them discover suitable items they might otherwise overlook. While many recommender systems primarily rely on a user's purchase history, recent multi-behavior recommender systems incorporate various auxiliary user behaviors, such as item clicks and cart additions, to enhance recommendations. Despite their overall performance gains, their effectiveness varies considerably between visited items (i.e., those a user has interacted with through auxiliary behaviors) and unvisited items (i.e., those with which the user has had no such interactions). Specifically, our analysis reveals that (1) existing multi-behavior recommender systems exhibit a significant gap in recommendation quality between the two item types (visited and unvisited items) and (2) achieving strong performance on both types with a single model architecture remains challenging. To tackle these issues, we propose a novel multi-behavior recommender system, MEMBER. It employs a mixture-of-experts framework, with experts designed to recommend the two item types, respectively. Each expert is trained using a self-supervised method specialized for its design goal. In our comprehensive experiments, we show the effectiveness of MEMBER across both item types, achieving up to 65.46% performance gain over the best competitor in terms of Hit Ratio@20.