Counterfactual Collaborative Reasoning
Jianchao Ji, Zelong Li, Shuyuan Xu, Max Xiong, Juntao Tan, Yingqiang, Ge, Hao Wang, Yongfeng Zhang

TL;DR
This paper introduces Counterfactual Collaborative Reasoning (CCR), a novel approach combining counterfactual and logical reasoning to improve accuracy and transparency in machine learning, demonstrated through recommender systems.
Contribution
The paper proposes CCR, a new framework that uses counterfactual logic reasoning for explicit data augmentation, enhancing model performance and explainability across models.
Findings
CCR outperforms non-augmented models.
CCR surpasses implicit augmentation methods.
CCR improves transparency with counterfactual explanations.
Abstract
Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under machine intelligence context. In this paper, we explore how the two reasoning abilities can be jointly modeled to enhance both accuracy and explainability of machine learning models. More specifically, by integrating two important types of reasoning ability -- counterfactual reasoning and (neural) logical reasoning -- we propose Counterfactual Collaborative Reasoning (CCR), which conducts counterfactual logic reasoning to improve the performance. In particular, we use recommender system as an example to show how CCR alleviate data scarcity, improve accuracy and enhance transparency. Technically, we leverage counterfactual reasoning to generate "difficult" counterfactual training examples for data augmentation,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsFocus
