# MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation

arXiv: https://arxiv.org/abs/2603.25126 · HTML: https://mlsanity.com/paper/2603.25126/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Causal Intervention for Leveraging Popularity Bias in Recommendation](https://mlsanity.com/paper/2105.06067/) (2021)
- [Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System](https://mlsanity.com/paper/2010.15363/) (2020)
- [Causal Embeddings for Recommendation](https://mlsanity.com/paper/1706.07639/) (2017)
- [Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network](https://mlsanity.com/paper/2110.04002/) (2021)
- [Graph Signal Diffusion Model for Collaborative Filtering](https://mlsanity.com/paper/2311.08744/) (2023)
- [A Survey on Causal Inference for Recommendation](https://mlsanity.com/paper/2303.11666/) (2023)
- [Knowledge Enhancement for Contrastive Multi-Behavior Recommendation](https://mlsanity.com/paper/2301.05403/) (2023)
- [SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback](https://mlsanity.com/paper/2002.09841/) (2020)
- [Cascading Residual Graph Convolutional Network for Multi-Behavior Recommendation](https://mlsanity.com/paper/2205.13128/) (2022)
- [PUB: An LLM-Enhanced Personality-Driven User Behaviour Simulator for Recommender System Evaluation](https://mlsanity.com/paper/2506.04551/) (2025)
- [Disentangled Causal Embedding With Contrastive Learning For Recommender System](https://mlsanity.com/paper/2302.03248/) (2023)
- [Disentangled Representation for Causal Mediation Analysis](https://mlsanity.com/paper/2302.09694/) (2023)
- [Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling](https://mlsanity.com/paper/2201.02307/) (2022)
- [Temporal-Aware User Behaviour Simulation with Large Language Models for Recommender Systems](https://mlsanity.com/paper/2509.16895/) (2025)
- [Behavior-Contextualized Item Preference Modeling for Multi-Behavior Recommendation](https://mlsanity.com/paper/2404.18166/) (2024)
- [Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Bandits](https://mlsanity.com/paper/2408.04332/) (2024)

## Built on by (most cited first, 1 of 1)

- [CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decomposition](https://mlsanity.com/paper/2608.25871/) (2026)

## Abstract (arXiv)

Multi-Behavior Recommendation (MBR) leverages multiple user interaction types (e.g., views, clicks, purchases) to enrich preference modeling and alleviate data sparsity issues in traditional single-behavior approaches. However, existing MBR methods face fundamental challenges: they lack principled frameworks to model complex confounding effects from user behavioral habits and item multi-behavior distributions, struggle with effective aggregation of heterogeneous auxiliary behaviors, and fail to align behavioral representations across semantic gaps while accounting for bias distortions. To address these limitations, we propose MCLMR, a novel model-agnostic causal learning framework that can be seamlessly integrated into various MBR architectures. MCLMR first constructs a causal graph to model confounding effects and performs interventions for unbiased preference estimation. Under this causal framework, it employs an Adaptive Aggregation module based on Mixture-of-Experts to dynamically fuse auxiliary behavior information and a Bias-aware Contrastive Learning module to align cross-behavior representations in a bias-aware manner. Extensive experiments on three real-world datasets demonstrate that MCLMR achieves significant performance improvements across various baseline models, validating its effectiveness and generality. All data and code will be made publicly available. For anonymous review, our code is available at the following the link: https://github.com/gitrxh/MCLMR.