mlsanityData to 7 Oct 2026

CLEAR: Causal Explanations from Attention in Neural Recommenders

arXiv 2210.10621 ↗First posted 7 Oct 2022cs.IR cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We present CLEAR, a method for learning session-specific causal graphs, in the possible presence of latent confounders, from attention in pre-trained attention-based recommenders. These causal graphs describe user behavior, within the context captured by attention, and can provide a counterfactual explanation for a recommendation. In essence, these causal graphs allow answering "why" questions uniquely for any specific session. Using empirical evaluations we show that, compared to naively using attention weights to explain input-output relations, counterfactual explanations found by CLEAR are shorter and an alternative recommendation is ranked higher in the original top-k recommendations.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

16 of 33 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  3. 2018Self-Attentive Sequential Recommendationcited by 1,169
  4. 2017Neural Collaborative Filteringcited by 1,108
  5. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
  6. 2019Attention is not Explanationcited by 916
  7. 2016The Mythos of Model Interpretabilitycited by 716
  8. 2019Attention is not not Explanationcited by 629
  9. 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
  10. 2017Deep Learning based Recommender System: A Survey and New Perspectivescited by 136
  11. 2013Learning Sparse Causal Models is not NP-hardcited by 48
  12. 2021Counterfactual Explanations for Neural Recommenderscited by 27
4 more
  1. 2019Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendationcited by 23
  2. 2021Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Biascited by 21
  3. 2018Bayesian Structure Learning by Recursive Bootstrapcited by 8
  4. 2021Improving Efficiency and Accuracy of Causal Discovery Using a Hierarchical Wrappercited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2023Causal Interpretation of Self-Attention in Pre-Trained Transformerscited by 30
  2. 2024LVLM-Interpret: An Interpretability Tool for Large Vision-Language Modelscited by 23
  3. 2023From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounderscited by 9
  4. 2024A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environmentcited by 6