IJCAI 2025 Workshop

Causal Learning for Recommendation Systems

Montreal, Canada

August 16–22, 2025

Submit Your Paper

Introduction

Recommendation systems are foundational to modern digital platforms, influencing user experiences across diverse domains such as e-commerce, social media, and streaming services. Despite their widespread use, traditional recommendation models predominantly rely on correlation-based learning, which can inadvertently lead to suboptimal, biased, or even unfair recommendations. In contrast, causal learning offers a paradigm shift, enabling the development of more reliable, equitable, and interpretable systems by explicitly modeling cause-effect relationships. By understanding the underlying mechanisms that drive user behavior, causal models hold the potential to unlock deeper insights and more personalized recommendations.

This workshop aims to bring together leading researchers and practitioners from the fields of machine learning, causal inference, and recommender systems to explore the promising intersection of causal learning and recommendation technologies. We invite contributions that showcase innovative approaches, cutting-edge research, and practical solutions, demonstrating how causal reasoning can address critical challenges such as bias, fairness, and interpretability in recommendation systems.

Important Dates

Paper Submission Deadline

May 9, 2025

Notification of Acceptance

June 6, 2025

Camera-ready Submission

June 20, 2025

Workshop Date

August 16–22, 2025

Call For Papers

This workshop aims to bring together leading researchers and practitioners to explore the promising intersection of causal learning and recommendation technologies. Below is a non-exhaustive list of topic categories and subcategories we aim to explore:

Causal Inference for Recommender Systems

  • Integrating causal models to improve recommendation quality
  • Modeling cause-effect relationships in user behavior
  • Causal discovery techniques for system design

LLM Applications

  • Causal learning helps LLMs generate disentangled representations
  • LLMs can discover causal relationships from textual data
  • Dynamic causal inference in sequential tasks

Bias and Fairness

  • Identifying and mitigating biases using causal frameworks
  • Fairness-aware recommendation models
  • Evaluating fairness using counterfactuals

Interpretability and Transparency

  • Explaining recommendations through causal reasoning
  • Causal explanations of user-item interactions
  • Methods for interpretable recommendation models

Counterfactual Learning

  • Counterfactual analysis for recommendation effectiveness
  • Generating personalized counterfactuals
  • Measuring intervention impacts

Causal Reinforcement Learning

  • Combining causal inference with reinforcement learning
  • Adaptive recommendation strategies
  • Dynamic recommendation systems

Practical Applications

  • Real-world applications in e-commerce and social media
  • Large-scale deployment case studies
  • Industry lessons and best practices

Ethical Implications

  • Ethical concerns and trade-offs
  • Addressing societal impacts and biases
  • Incorporating ethical considerations

Submission

Paper Format

  • Please use the official IJCAI format
  • Submit anonymous manuscripts (double-blind paper review)
  • We accept papers of pages ≥4 (reference and appendix excluded)

Schedule

This is a tentative schedule and subject to change

9:00 – 9:15

Welcome and Opening Remarks

Welcome and introduction by workshop organizers

9:15 – 10:00

Invited Keynote 1

To be announced

10:00 – 10:45

Contributed Paper Session 1

Paper presentations

10:45 – 11:00

Coffee Break

11:00 – 11:45

Invited Keynote 2

To be announced

11:45 – 13:00

Lunch Break

13:00 – 14:00

Contributed Paper Session 2

Paper presentations

14:00 – 14:45

Poster Session and Networking Break

Interactive discussions with poster presenters

14:45 – 15:00

Closing Remarks

Concluding remarks and best paper award announcement

Committee

Organizing Committee

Zhigang Hua

Meta

zhua@meta.com

Qi Xu

Meta

xuqi@meta.com

Zihao Xu

Rutgers University

zx158@cs.rutgers.edu

Wei Shi

Meta

weishi0079@meta.com

Shuang Yang

Meta

shuangyang@meta.com

Bo Long

Meta

bolong@meta.com

Yiping Han

Meta

yipinghan@meta.com

Program Committee

To Be Announced

The Program Committee is currently being formed. Please check back later for updates.