# Counterfactual Explanations for Neural Recommenders

arXiv: https://arxiv.org/abs/2105.05008 · HTML: https://mlsanity.com/paper/2105.05008/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 11 May 2021.

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

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [Deep Learning based Recommender System: A Survey and New Perspectives](https://mlsanity.com/paper/1707.07435/) (2017)
- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [Reinforcement Knowledge Graph Reasoning for Explainable Recommendation](https://mlsanity.com/paper/1906.05237/) (2019)
- [Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation](https://mlsanity.com/paper/1805.03352/) (2018)
- [PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems](https://mlsanity.com/paper/1911.08378/) (2019)
- [Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation](https://mlsanity.com/paper/1904.12796/) (2019)
- [Explaining Latent Factor Models for Recommendation with Influence Functions](https://mlsanity.com/paper/1811.08120/) (2018)
- [A Context-Aware User-Item Representation Learning for Item Recommendation](https://mlsanity.com/paper/1712.02342/) (2017)
- [FAIRY: A Framework for Understanding Relationships between Users' Actions and their Social Feeds](https://mlsanity.com/paper/1908.03109/) (2019)
- [ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models](https://mlsanity.com/paper/2102.09388/) (2021)

## Built on by (most cited first, 27 of 27)

- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Causal Interpretation of Self-Attention in Pre-Trained Transformers](https://mlsanity.com/paper/2310.20307/) (2023)
- [Reinforced Path Reasoning for Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2207.06674/) (2022)
- [SiReN: Sign-Aware Recommendation Using Graph Neural Networks](https://mlsanity.com/paper/2108.08735/) (2021)
- [From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems](https://mlsanity.com/paper/2110.14844/) (2021)
- [Model-Agnostic and Diverse Explanations for Streaming Rumour Graphs](https://mlsanity.com/paper/2207.08098/) (2022)
- [Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems](https://mlsanity.com/paper/2412.10571/) (2024)
- [May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability](https://mlsanity.com/paper/2309.13965/) (2023)
- [CLEAR: Causal Explanations from Attention in Neural Recommenders](https://mlsanity.com/paper/2210.10621/) (2022)
- [Towards Explainable Conversational Recommender Systems](https://mlsanity.com/paper/2305.18363/) (2023)
- [Interpretable Knowledge Tracing via Response Influence-based Counterfactual Reasoning](https://mlsanity.com/paper/2312.10045/) (2023)
- [Counterfactual Collaborative Reasoning](https://mlsanity.com/paper/2307.00165/) (2023)
- [RecRec: Algorithmic Recourse for Recommender Systems](https://mlsanity.com/paper/2308.14916/) (2023)
- [Fidelity-Aware Recommendation Explanations via Stochastic Path Integration](https://mlsanity.com/paper/2511.18047/) (2025)
- [Counterfactually Evaluating Explanations in Recommender Systems](https://mlsanity.com/paper/2203.01310/) (2022)
- [Dynamic Causal Collaborative Filtering](https://mlsanity.com/paper/2208.11094/) (2022)
- [Learning to Counterfactually Explain Recommendations](https://mlsanity.com/paper/2211.09752/) (2022)
- [COmic: Convolutional Kernel Networks for Interpretable End-to-End Learning on (Multi-)Omics Data](https://mlsanity.com/paper/2212.02504/) (2022)
- [T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems](https://mlsanity.com/paper/2309.16146/) (2023)
- [CRUISE on Quantum Computing for Feature Selection in Recommender Systems](https://mlsanity.com/paper/2407.02839/) (2024)
- [Explain and Conquer: Personalised Text-based Reviews to Achieve Transparency](https://mlsanity.com/paper/2205.01759/) (2022)
- [Explainable History Distillation by Marked Temporal Point Process](https://mlsanity.com/paper/2311.07797/) (2023)
- [Performance-Driven QUBO for Recommender Systems on Quantum Annealers](https://mlsanity.com/paper/2410.15272/) (2024)
- [Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoning](https://mlsanity.com/paper/2508.11943/) (2025)
- [From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems](https://mlsanity.com/paper/2604.19663/) (2026)
- [Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals](https://mlsanity.com/paper/2608.21662/) (2026)
- [Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence](https://mlsanity.com/paper/2609.05385/) (2026)

## Abstract (arXiv)

Understanding why specific items are recommended to users can significantly increase their trust and satisfaction in the system. While neural recommenders have become the state-of-the-art in recent years, the complexity of deep models still makes the generation of tangible explanations for end users a challenging problem. Existing methods are usually based on attention distributions over a variety of features, which are still questionable regarding their suitability as explanations, and rather unwieldy to grasp for an end user. Counterfactual explanations based on a small set of the user's own actions have been shown to be an acceptable solution to the tangibility problem. However, current work on such counterfactuals cannot be readily applied to neural models. In this work, we propose ACCENT, the first general framework for finding counterfactual explanations for neural recommenders. It extends recently-proposed influence functions for identifying training points most relevant to a recommendation, from a single to a pair of items, while deducing a counterfactual set in an iterative process. We use ACCENT to generate counterfactual explanations for two popular neural models, Neural Collaborative Filtering (NCF) and Relational Collaborative Filtering (RCF), and demonstrate its feasibility on a sample of the popular MovieLens 100K dataset.