Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
arXiv:2401.05744 · doi:10.1109/TKDE.2024.3373608
Abstract
Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on three real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.
arXiv commentaccepted by TKDE
References in corpus (18)
- Efficient Estimation of Word Representations in Vector Space
- DeepWalk: Online Learning of Social Representations
- LINE: Large-scale Information Network Embedding
- KGAT: Knowledge Graph Attention Network for Recommendation
- Session-based Recommendation with Graph Neural Networks
- Explainable Recommendation: A Survey and New Perspectives
- Learning over Knowledge-Base Embeddings for Recommendation
- Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
- Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
- Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
- Intent Contrastive Learning for Sequential Recommendation
- Random Walks: A Review of Algorithms and Applications
- Counterfactual Explainable Recommendation
- PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems
- Time-aware Path Reasoning on Knowledge Graph for Recommendation
- Explainable Fairness in Recommendation
- Robust Counterfactual Explanations on Graph Neural Networks
- From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems