mlsanityData to 14 Oct 2026

SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction

arXiv 2510.00080 ↗First posted 30 Sep 2025cs.SI cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Social recommendation has been proven effective in addressing data sparsity in user-item interaction modeling by leveraging social networks. The recent integration of Graph Neural Networks (GNNs) has further enhanced prediction accuracy in contemporary social recommendation algorithms. However, many GNN-based approaches in social recommendation lack the ability to furnish meaningful explanations for their predictions. In this study, we confront this challenge by introducing SoREX, a self-explanatory GNN-based social recommendation framework. SoREX adopts a two-tower framework enhanced by friend recommendation, independently modeling social relations and user-item interactions, while jointly optimizing an auxiliary task to reinforce social signals. To offer explanations, we propose a novel ego-path extraction approach. This method involves transforming the ego-net of a target user into a collection of multi-hop ego-paths, from which we extract factor-specific and candidate-aware ego-path subsets as explanations. This process facilitates the summarization of detailed comparative explanations among different candidate items through intricate substructure analysis. Furthermore, we conduct explanation re-aggregation to explicitly correlate explanations with downstream predictions, imbuing our framework with inherent self-explainability. Comprehensive experiments conducted on four widely adopted benchmark datasets validate the effectiveness of SoREX in predictive accuracy. Additionally, qualitative and quantitative analyses confirm the efficacy of the extracted explanations in SoREX. Our code and data are available at https://github.com/antman9914/SoREX.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 42 of its 72 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

42 of 72 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  5. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  7. 2019Graph Neural Networks for Social Recommendationcited by 714
  8. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  9. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  10. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  11. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  12. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
30 more
  1. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  2. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  3. 2019Reinforcement Knowledge Graph Reasoning for Explainable Recommendationcited by 102
  4. 2021Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendationcited by 101
  5. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  6. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  7. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  8. 2019A Neural Influence Diffusion Model for Social Recommendationcited by 70
  9. 2017Neural Rating Regression with Abstractive Tips Generation for Recommendationcited by 50
  10. 2020DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendationcited by 46
  11. 2018Explainable Recommendation via Multi-Task Learning in Opinionated Text Datacited by 40
  12. 2021Socially-Aware Self-Supervised Tri-Training for Recommendationcited by 32
  13. 2022Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learningcited by 28
  14. 2019The FacT: Taming Latent Factor Models for Explainability with Factorization Treescited by 27
  15. 2022Disentangled Contrastive Learning for Social Recommendationcited by 27
  16. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  17. 2023Interpretable Prototype-based Graph Information Bottleneckcited by 23
  18. 2025R2MED: A Benchmark for Reasoning-Driven Medical Retrievalcited by 22
  19. 2024RecDiff: Diffusion Model for Social Recommendationcited by 20
  20. 2018Explainable Reasoning over Knowledge Graphs for Recommendationcited by 19
  21. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  22. 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13
  23. 2019Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendationcited by 10
  24. 2024Challenging Low Homophily in Social Recommendationcited by 10
  25. 2021Explanation as a Defense of Recommendationcited by 9
  26. 2021Comparative Explanations of Recommendationscited by 8
  27. 2025Tricolore: Multi-Behavior User Profiling for Enhanced Candidate Generation in Recommender Systemscited by 6
  28. 2024Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential Recommendationscited by 5
  29. 2023Towards Explainable Collaborative Filtering with Taste Clusters Learningcited by 2
  30. 2023Self-Explainable Graph Neural Networks for Link Predictioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Modelscited by 5
  2. 2026Why not Collaborative Filtering in Dual View? Bridging Sparse and Dense Modelscited by 3
  3. 2026HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationshipscited by 3
  4. 2026Controllable Affective Generation via Latent Vector Steeringcited by 0
  5. 2026From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMscited by 0