# Causal Disentanglement with Network Information for Debiased Recommendations

arXiv: https://arxiv.org/abs/2204.07221 · HTML: https://mlsanity.com/paper/2204.07221/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [A Note on Over-Smoothing for Graph Neural Networks](https://mlsanity.com/paper/2006.13318/) (2020)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Invariance, Causality and Robustness](https://mlsanity.com/paper/1812.08233/) (2018)
- [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)
- [ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation](https://mlsanity.com/paper/2105.02254/) (2021)
- [User-centered Evaluation of Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2103.06364/) (2021)
- [Top-N Recommendation with Counterfactual User Preference Simulation](https://mlsanity.com/paper/2109.02444/) (2021)
- [Explainable Recommender Systems via Resolving Learning Representations](https://mlsanity.com/paper/2008.09316/) (2020)
- [Be Causal: De-biasing Social Network Confounding in Recommendation](https://mlsanity.com/paper/2105.07775/) (2021)
- [Intent Disentanglement and Feature Self-supervision for Novel Recommendation](https://mlsanity.com/paper/2106.14388/) (2021)

## Built on by (most cited first, 4 of 4)

- [Domain Generalization -- A Causal Perspective](https://mlsanity.com/paper/2209.15177/) (2022)
- [Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation](https://mlsanity.com/paper/2403.03578/) (2024)
- [The Importance of Causality in Decision Making: A Perspective on Recommender Systems](https://mlsanity.com/paper/2410.01822/) (2024)
- [Introducing CausalBench: A Flexible Benchmark Framework for Causal Analysis and Machine Learning](https://mlsanity.com/paper/2409.08419/) (2024)

## Abstract (arXiv)

Recommender systems aim to recommend new items to users by learning user and item representations. In practice, these representations are highly entangled as they consist of information about multiple factors, including user's interests, item attributes along with confounding factors such as user conformity, and item popularity. Considering these entangled representations for inferring user preference may lead to biased recommendations (e.g., when the recommender model recommends popular items even if they do not align with the user's interests). Recent research proposes to debias by modeling a recommender system from a causal perspective. The exposure and the ratings are analogous to the treatment and the outcome in the causal inference framework, respectively. The critical challenge in this setting is accounting for the hidden confounders. These confounders are unobserved, making it hard to measure them. On the other hand, since these confounders affect both the exposure and the ratings, it is essential to account for them in generating debiased recommendations. To better approximate hidden confounders, we propose to leverage network information (i.e., user-social and user-item networks), which are shown to influence how users discover and interact with an item. Aside from the user conformity, aspects of confounding such as item popularity present in the network information is also captured in our method with the aid of textitcausal disentanglement which unravels the learned representations into independent factors that are responsible for (a) modeling the exposure of an item to the user, (b) predicting the ratings, and (c) controlling the hidden confounders. Experiments on real-world datasets validate the effectiveness of the proposed model for debiasing recommender systems.