Papers
Topics
Authors
Recent
Search
2000 character limit reached

GNNUERS: Fairness Explanation in GNNs for Recommendation via Counterfactual Reasoning

Published 12 Apr 2023 in cs.IR | (2304.06182v4)

Abstract: Nowadays, research into personalization has been focusing on explainability and fairness. Several approaches proposed in recent works are able to explain individual recommendations in a post-hoc manner or by explanation paths. However, explainability techniques applied to unfairness in recommendation have been limited to finding user/item features mostly related to biased recommendations. In this paper, we devised a novel algorithm that leverages counterfactuality methods to discover user unfairness explanations in the form of user-item interactions. In our counterfactual framework, interactions are represented as edges in a bipartite graph, with users and items as nodes. Our bipartite graph explainer perturbs the topological structure to find an altered version that minimizes the disparity in utility between the protected and unprotected demographic groups. Experiments on four real-world graphs coming from various domains showed that our method can systematically explain user unfairness on three state-of-the-art GNN-based recommendation models. Moreover, an empirical evaluation of the perturbed network uncovered relevant patterns that justify the nature of the unfairness discovered by the generated explanations. The source code and the preprocessed data sets are available at https://github.com/jackmedda/RS-BGExplainer.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Towards a unified framework for fair and stable graph representation learning. In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2021, Vol. 161. AUAI Press, 2114–2124.
  2. Ashwathy Ashokan and Christian Haas. 2021. Fairness metrics and bias mitigation strategies for rating predictions. Inf. Process. Manag. 58, 5 (2021), 102646. https://doi.org/10.1016/j.ipm.2021.102646
  3. Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations. In SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022. ACM, 646–656. https://doi.org/10.1145/3477495.3532041
  4. Consumer Fairness in Recommender Systems: Contextualizing Definitions and Mitigations. In Advances in Information Retrieval. Springer International Publishing, Cham, 552–566.
  5. Preference-based and local post-hoc explanations for recommender systems. Inf. Syst. 108 (2022), 102021. https://doi.org/10.1016/j.is.2022.102021
  6. Balanced Neighborhoods for Multi-sided Fairness in Recommendation. In Conference on Fairness, Accountability and Transparency, FAT 2018, Vol. 81. PMLR, 202–214. http://proceedings.mlr.press/v81/burke18a.html
  7. Òscar Celma. 2010. Music Recommendation and Discovery - The Long Tail, Long Fail, and Long Play in the Digital Music Space. Springer. https://doi.org/10.1007/978-3-642-13287-2
  8. CatGCN: Graph Convolutional Networks with Categorical Node Features. IEEE Transactions on Knowledge and Data Engineering (2021).
  9. Semi-supervised user profiling with heterogeneous graph attention networks. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2116–2122.
  10. Measuring ”Why” in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation. CoRR abs/2202.06466 (2022). arXiv:2202.06466 https://arxiv.org/abs/2202.06466
  11. GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations. CoRR abs/2208.04222 (2022). arXiv:2208.04222 https://doi.org/10.48550/arXiv.2208.04222
  12. How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation. In European Conference on Information Retrieval. Springer, 75–83.
  13. Explaining recommender systems fairness and accuracy through the lens of data characteristics. Inf. Process. Manag. 58, 5 (2021), 102662. https://doi.org/10.1016/j.ipm.2021.102662
  14. Interpreting Unfairness in Graph Neural Networks via Training Node Attribution. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023. 7441–7449. https://ojs.aaai.org/index.php/AAAI/article/view/25905
  15. Fairness in Information Access Systems. Found. Trends Inf. Retr. 16, 1-2 (2022), 1–177. https://doi.org/10.1561/1500000079
  16. All The Cool Kids, How Do They Fit In?: Popularity and Demographic Biases in Recommender Evaluation and Effectiveness. In Conference on Fairness, Accountability and Transparency, FAT 2018, Vol. 81. PMLR, 172–186. http://proceedings.mlr.press/v81/ekstrand18b.html
  17. Exposure Inequality in People Recommender Systems: The Long-Term Effects. In Proceedings of the Sixteenth International AAAI Conference on Web and Social Media, ICWSM 2022. AAAI Press, 194–204.
  18. Stereotype-aware collaborative filtering. In Proceedings of the 16th Conference on Computer Science and Intelligence Systems, Online, September 2-5, 2021. 69–79. https://doi.org/10.15439/2021F117
  19. Explainable Fairness in Recommendation. In SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 681–691. https://doi.org/10.1145/3477495.3531973
  20. PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems. In WSDM ’20: The Thirteenth ACM International Conference on Web Search and Data Mining. ACM, 196–204.
  21. ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models. In WWW ’21: The Web Conference 2021. ACM / IW3C2.
  22. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  23. F. Maxwell Harper and Joseph A. Konstan. 2016. The MovieLens Datasets: History and Context. ACM Trans. Interact. Intell. Syst. 5, 4 (2016), 19:1–19:19. https://doi.org/10.1145/2827872
  24. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, SIGIR 2020, Virtual Event, China, July 25-30, 2020. ACM, 639–648. https://doi.org/10.1145/3397271.3401063
  25. Global Counterfactual Explainer for Graph Neural Networks. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, WSDM 2023, Singapore, 27 February 2023 - 3 March 2023, Tat-Seng Chua, Hady W. Lauw, Luo Si, Evimaria Terzi, and Panayiotis Tsaparas (Eds.). ACM, 141–149. https://doi.org/10.1145/3539597.3570376
  26. Kalervo Järvelin and Jaana Kekäläinen. 2002. Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. 20, 4 (2002), 422–446. https://doi.org/10.1145/582415.582418
  27. Recommendation Independence. In Conference on Fairness, Accountability and Transparency, FAT 2018, Vol. 81. PMLR, 187–201.
  28. Explanations for Network Embedding-Based Link Predictions. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2021, Vol. 1524. Springer, 473–488.
  29. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017, Conference Track Proceedings.
  30. User-oriented Fairness in Recommendation. In WWW ’21: The Web Conference 2021. ACM / IW3C2, 624–632. https://doi.org/10.1145/3442381.3449866
  31. Towards Personalized Fairness based on Causal Notion. In SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 1054–1063.
  32. CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks. In International Conference on Artificial Intelligence and Statistics, AISTATS 2022, Vol. 151. PMLR, 4499–4511.
  33. Learning Fair Node Representations with Graph Counterfactual Fairness. In WSDM ’22: The Fifteenth ACM International Conference on Web Search and Data Mining. ACM, 695–703.
  34. Bias Disparity in Collaborative Recommendation: Algorithmic Evaluation and Comparison. In Proceedings of the Workshop on Recommendation in Multi-stakeholder Environments co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019) (CEUR Workshop Proceedings, Vol. 2440). CEUR-WS.org.
  35. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 6 (2021), 115:1–115:35. https://doi.org/10.1145/3457607
  36. M. E. J. Newman. 2003. Mixing patterns in networks. Phys. Rev. E 67 (Feb 2003), 026126. Issue 2. https://doi.org/10.1103/PhysRevE.67.026126
  37. Rank List Sensitivity of Recommender Systems to Interaction Perturbations. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. ACM, 1584–1594.
  38. A general approximation framework for direct optimization of information retrieval measures. Inf. Retr. 13, 4 (2010), 375–397. https://doi.org/10.1007/s10791-009-9124-x
  39. Experiments on Generalizability of User-Oriented Fairness in Recommender Systems. In SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2755–2764. https://doi.org/10.1145/3477495.3531718
  40. Ashudeep Singh and Thorsten Joachims. 2018. Fairness of Exposure in Rankings. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, London, UK, August 19-23, 2018. ACM, 2219–2228.
  41. Training Sparse Neural Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2017. IEEE Computer Society, 455–462. https://doi.org/10.1109/CVPRW.2017.61
  42. Counterfactual Explainable Recommendation. In CIKM ’21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021, Gianluca Demartini, Guido Zuccon, J. Shane Culpepper, Zi Huang, and Hanghang Tong (Eds.). ACM, 1784–1793. https://doi.org/10.1145/3459637.3482420
  43. Graph Convolutional Matrix Completion. CoRR abs/1706.02263 (2017). arXiv:1706.02263
  44. Graph Attention Networks. In International Conference on Learning Representations.
  45. Unbiased Graph Embedding with Biased Graph Observations. In WWW ’22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25 - 29, 2022. ACM, 1423–1433.
  46. COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation. CoRR abs/2210.15500 (2022). https://doi.org/10.48550/arXiv.2210.15500 arXiv:2210.15500
  47. Trustworthy Recommender Systems. CoRR abs/2208.06265 (2022).
  48. Neural Graph Collaborative Filtering. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019. ACM.
  49. A Survey on the Fairness of Recommender Systems. ACM Trans. Inf. Syst. (jul 2022). https://doi.org/10.1145/3547333 Just Accepted.
  50. Fairness-aware News Recommendation with Decomposed Adversarial Learning. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021. AAAI Press, 4462–4469.
  51. A Multi-Objective Optimization Framework for Multi-Stakeholder Fairness-Aware Recommendation. ACM Trans. Inf. Syst. (aug 2022). https://doi.org/10.1145/3564285 Just Accepted.
  52. Relation-aware Heterogeneous Graph for User Profiling. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. Association for Computing Machinery, New York, NY, USA.
  53. Graph convolutional networks for text classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 7370–7377.
  54. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 974–983.
  55. XGNN: Towards Model-Level Explanations of Graph Neural Networks. In KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020. ACM, 430–438.
  56. Explainability in Graph Neural Networks: A Taxonomic Survey. IEEE Trans. Pattern Anal. Mach. Intell. 45, 5 (2023), 5782–5799. https://doi.org/10.1109/TPAMI.2022.3204236
  57. PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction. In Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023, Ying Ding, Jie Tang, Juan F. Sequeda, Lora Aroyo, Carlos Castillo, and Geert-Jan Houben (Eds.). ACM, 3784–3793. https://doi.org/10.1145/3543507.3583511
  58. Yongfeng Zhang and Xu Chen. 2020. Explainable Recommendation: A Survey and New Perspectives. Found. Trends Inf. Retr. 14, 1 (mar 2020), 1–101.
  59. Deep Learning on Graphs: A Survey. IEEE Transactions on Knowledge and Data Engineering 34, 1 (2022), 249–270.
  60. RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms. In CIKM ’21: The 30th ACM International Conference on Information and Knowledge Management. ACM, 4653–4664.
  61. Jinfeng Zhong and Elsa Negre. 2022. Shap-enhanced counterfactual explanations for recommendations. In SAC ’22: The 37th ACM/SIGAPP Symposium on Applied Computing, Virtual Event, April 25 - 29, 2022, Jiman Hong, Miroslav Bures, Juw Won Park, and Tomás Cerný (Eds.). ACM, 1365–1372. https://doi.org/10.1145/3477314.3507029
Citations (5)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up