PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems
Open accessAbstract
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding other users' privacy. In this work, we take a fresh perspective, and present PRINCE: a provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommendation to a different item. Given a recommendation, PRINCE uses a polynomial-time optimal algorithm for finding this minimal set of a user's actions from an exponential search space, based on random walks over dynamic graphs. Experiments on two real-world datasets show that PRINCE provides more compact explanations than intuitive baselines, and insights from a crowdsourced user-study demonstrate the viability of such action-based explanations. We thus posit that PRINCE produces scrutable, actionable, and concise explanations, owing to its use of counterfactual evidence, a user's own actions, and minimal sets, respectively.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Mosca et al. introduce an argumentation-based framework for social network management [149].
“Mosca et al. introduce an argumentation-based framework for social network management [149].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [149]
Mosca et al. use contrastive explanations to answer critical questions about agent actions in the context of multi-user privacy conflict.
“They use contrastive explanations to answer critical questions about agent actions in the context of multi-user privacy conflict.”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [149]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Content Analysis: An Introduction to its Methodology.
Shelley, M., & Krippendorff, K. (1984) · Journal of the American Statistical Association · doi:10.2307/2288384 · Cited by 24,305 · see citing works
The anatomy of a large-scale hypertextual Web search engine
Brin, S., & Page, L. (1998) · Computer Networks and ISDN Systems · doi:10.1016/s0169-7552(98)00110-x · Cited by 16,004 · see citing works
(1999) · Cited by 12,854 · see citing works
Matrix Factorization Techniques for Recommender Systems
Koren, Y., Bell, R. M., & Volinsky, C. (2009) · Computer · doi:10.1109/mc.2009.263 · Cited by 11,232 · see citing works
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682 · see citing works
Explaining collaborative filtering recommendations
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000) · Proceedings of the 2000 ACM conference on Computer supported cooperative work · doi:10.1145/358916.358995 · Cited by 1,731 · see citing works
Universal Sentence Encoder for English
Cer, D. M., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Céspedes, M., Yuan, S., Tar, C., et al. (2018) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/d18-2029 · Cited by 1,344 · see citing works
Wang, H., Zhang, F., Wang, J., Zhao, M., Li, W., Xie, X., & Guo, M. (2018) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3269206.3271739 · Cited by 1,251 · see citing works
Scaling personalized web search
Jeh, G., & Widom, J. (2003) · Proceedings of the twelfth international conference on World Wide Web - WWW '03 · doi:10.1145/775152.775191 · Cited by 1,195 · see citing works
A survey of heterogeneous information network analysis
Shi, C., Li, Y., Zhang, J., Sun, Y., & Yu, P. S. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2016.2598561 · Cited by 1,122 · see citing works
Topic-sensitive pagerank: A context-sensitive ranking algorithm for web search
Haveliwala, T. H. (2003) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2003.1208999 · Cited by 1,046 · see citing works
Local Graph Partitioning using PageRank Vectors
Andersen, R., Chung, F., & Lang, K. (2006) · 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06) · doi:10.1109/focs.2006.44 · Cited by 967 · see citing works
Explicit factor models for explainable recommendation based on phrase-level sentiment analysis
Zhang, Y., Lai, G., Zhang, M., Zhang, Y., Liu, Y., & Ma, S. (2014) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2600428.2609579 · Cited by 814 · see citing works
Explainable Reasoning over Knowledge Graphs for Recommendation
Wang, X., Wang, D., Xu, C., He, X., Cao, Y., & Chua, T.-S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015329 · Cited by 785 · see citing works
Jamali, M., & Ester, M. (2009) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1557019.1557067 · Cited by 771 · see citing works
Explainable Recommendation: A Survey and New Perspectives
Zhang, Y., & Chen, X. (2020) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000066 · Cited by 755 · see citing works
Personalized entity recommendation
Yu, X. F., Ren, X., Sun, Y., et al. (2014) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2556195.2556259 · Cited by 747 · see citing works
Explainable Recommendation a survey and new perspectives
Zhang, Y., & Chen, X. (2020) · Cited by 689 · see citing works
Neural Attentional Rating Regression with Review-level Explanations
Chen, C., Zhang, M., Liu, Y., & Ma, S. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186070 · Cited by 652 · see citing works
A Comprehensive Survey of Neighborhood-Based Recommendation Methods
Ning, X., Desrosiers, C., & Karypis, G. (2015) · Springer eBooks · doi:10.1007/978-1-4899-7637-6_2 · Cited by 647 · see citing works
A Survey of Explanations in Recommender Systems
Tintarev, N., & Masthoff, J. (2007) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew.2007.4401070 · Cited by 584 · see citing works
Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
Xian, Y., Fu, Z., Muthukrishnan, S., de Melo, G., & Zhang, Y. (2019) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3331184.3331203 · Cited by 546 · see citing works
A Comprehensive Survey of Neighborhood-based Recommendation Methods
Desrosiers, C., & Karypis, G. (2010) · Springer eBooks · doi:10.1007/978-0-387-85820-3_4 · Cited by 539 · see citing works
Sequential Recommendation with User Memory Networks
Chen, X., Xu, H., Zhang, Y., Tang, J., Cao, Y., Qin, Z., & Hongyuan Zha, B. (2018) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3159652.3159668 · Cited by 518 · see citing works
Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
Ai, Q., Azizi, V., Chen, X., & Zhang, Y. (2018) · Algorithms · doi:10.3390/a11090137 · Cited by 514 · see citing works
Seo, S., Huang, J., Yang, H., & Liu, Y. (2017) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3109859.3109890 · Cited by 481 · see citing works
Fast incremental and personalized PageRank
Bahmani, B., Chowdhury, A., & Goel, A. (2010) · Proceedings of the VLDB Endowment · doi:10.14778/1929861.1929864 · Cited by 350 · see citing works
Neural Rating Regression with Abstractive Tips Generation for Recommendation
Li, P., Wang, Z., Ren, Z., Bing, L., & Lam, W. (2017) · Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3077136.3080822 · Cited by 313 · see citing works
Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network
Chen, X., Chen, H., Xu, H., Zhang, Y., Cao, Y., Qin, Z., & Hongyuan Zha, B. (2019) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3331184.3331254 · Cited by 307 · see citing works
Semantic Path based Personalized Recommendation on Weighted Heterogeneous Information Networks
Shi, C., Zhang, Z., Luo, P., Yu, P. S., Yue, Y., & Wu, B. (2015) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2806416.2806528 · Cited by 298 · see citing works
Explaining Data-Driven Document Classifications1
Martens, D., & Provost, F. (2014) · MIS Quarterly · doi:10.25300/misq/2014/38.1.04 · Cited by 264 · see citing works
Monte Carlo Methods in PageRank Computation: When One Iteration is Sufficient
Avrachenkov, K., Litvak, N., Nemirovsky, D., & Osipova, N. (2007) · SIAM Journal on Numerical Analysis · doi:10.1137/050643799 · Cited by 250 · cited 1× · see citing works
“Approximate algorithms include power iteration [38], local push [2, 3, 56] and Monte Carlo methods [4, 5].”
MethodItem recommendation on monotonic behavior chains
Wan, M., & McAuley, J. (2018) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3240323.3240369 · Cited by 249 · see citing works
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph
Ma, W., Zhang, M., Cao, Y., Jin, W., Wang, C., Liu, Y., Ma, S., & Ren, X. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308558.3313607 · Cited by 231 · see citing works
Explainable Recommendation via Multi-Task Learning in Opinionated Text Data
Wang, N., Wang, H., Jia, Y., & Yin, Y. (2018) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3209978.3210010 · Cited by 217 · see citing works
Recommendation in heterogeneous information networks with implicit user feedback
Yu, X. Y., Ren, X., Sun, Y., et al. (2013) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/2507157.2507230 · Cited by 207 · see citing works
Explainable Recommendation: A Survey and New Perspectives
Zhang, Y., & Chen, X. (2020) · doi:10.1561/9781680836592 · Cited by 200 · see citing works
Eksombatchai, C., Jindal, P., Liu, J. Z., Liu, Y., Sharma, R. A., Sugnet, C., Ulrich, M., & Leskovec, J. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186183 · Cited by 194 · see citing works
Personalized explanations for hybrid recommender systems
Kouki, P., Schaffer, J., Pujara, J., O’Donovan, J., & Getoor, L. C. (2019) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3301275.3302306 · Cited by 175 · see citing works
Personalized social recommendations
Machanavajjhala, A., Korolova, A., & Sarma, A. D. (2011) · Proceedings of the VLDB Endowment · doi:10.14778/1988776.1988780 · Cited by 174 · see citing works
A Reinforcement Learning Framework for Explainable Recommendation
Wang, X., Chen, Y., Yang, J., Wu, L., Wu, Z., & Xie, X. (2018) · 2018 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2018.00074 · Cited by 163 · see citing works
Learning to Rank Features for Recommendation over Multiple Categories
Chen, X., Qin, Z., Zhang, Y., et al. (2016) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2911451.2911549 · Cited by 158 · see citing works
Let Me Explain: Impact of Personal and Impersonal Explanations on Trust in Recommender Systems
Kunkel, J., Donkers, T., Michael, L., Barbu, C.-M., & Ziegler, J. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300717 · Cited by 156 · see citing works
Peake, G. S., & Wang, Y.-X. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3220072 · Cited by 152 · see citing works
Transparent, Scrutable and Explainable User Models for Personalized Recommendation
Balog, K., Radlinski, F., & Arakelyan, S. (2019) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3331184.3331211 · Cited by 152 · see citing works
Scaling personalized web search
Jeh, G., & Widom, J. (2003) · International World Wide Web Conference (WWW) · doi:10.1145/775189.775191 · Cited by 134 · see citing works
Lu, Y., Dong, R., & Smyth, B. (2018) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3240323.3240365 · Cited by 118 · see citing works
Local Computation of PageRank Contributions
Andersen, R., Borgs, C., Chayes, J., Hopcraft, J., Mirrokni, V., & Teng, S. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-77004-6_12 · Cited by 112 · see citing works
de Chardin, P. T. (1970) · Medical Entomology and Zoology · Cited by 97 · see citing works
Νικολακόπουλος, Α. Ν., & Karypis, G. (2019) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3289600.3291016 · Cited by 90 · see citing works
Zhang, C., Swami, A., & Chawla, N. V. (2019) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3289600.3291001 · Cited by 89 · see citing works
Approximate Personalized PageRank on Dynamic Graphs
Zhang, H. R., Lofgren, P., & Goel, A. (2016) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2939672.2939804 · Cited by 79 · see citing works
Jiang, Z., Liu, H., Fu, B., et al. (2018) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3159652.3159715 · Cited by 79 · see citing works
Local Computation of PageRank Contributions
Andersen, R., Borgs, C., Chayes, J., Hopcroft, J. E., Mirrokni, V., & Teng, S. (2008) · Internet Mathematics · doi:10.1080/15427951.2008.10129302 · Cited by 79 · see citing works
Random walks in recommender systems
Cooper, C., Lee, S.-H., Radzik, T., et al. (2014) · International World Wide Web Conference (WWW) · doi:10.1145/2567948.2579244 · Cited by 67 · see citing works
Christoffel, F., Paudel, B., Newell, C., et al. (2015) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/2792838.2800180 · Cited by 65 · see citing works
PageRank optimization by edge selection
Csáji, B. C., Jungers, R. M., & Blondel, V. D. (2014) · Discrete Applied Mathematics · doi:10.1016/j.dam.2014.01.007 · Cited by 62 · see citing works
Enhancing Transparency and Control When Drawing Data-Driven Inferences About Individuals
Chen, D., Fraiberger, S. P., Moakler, R., & Provost, F. J. (2017) · Big Data · doi:10.1089/big.2017.0074 · Cited by 37 · see citing works
Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-TimePreprint
Eksombatchai, C., Jindal, P., Liu, J. Z., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07601 · Cited by 25 · see citing works
Towards Interpretation of Recommender Systems with Sorted Explanation Paths
Yang, F., Liu, N., Wang, S., & Hu, X. (2018) · Proceedings · doi:10.1109/icdm.2018.00082 · Cited by 22 · see citing works
Personalized Social Recommendations - Accurate or Private?Preprint
Machanavajjhala, A., Korolova, A., & Sarma, A. D. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1105.4254 · Cited by 22 · see citing works
Explaining Classification Models Built on High-Dimensional Sparse DataPreprint
Moeyersoms, J., d'Alessandro, B., Provost, F. J., & Martens, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.06280 · Cited by 15 · see citing works
AURORA: Auditing PageRank on Large Graphs
Kang, J. L., Wang, M., Cao, N., Xia, Y., Fan, W., & Tong, H. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622563 · Cited by 14 · see citing works
Zhang, Y., Zhang, Y., Zhang, M., & Shah, C. S. (2019) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3331184.3331649 · Cited by 8 · see citing works
Ghazimatin, A., Roy, R. S., & Weikum, G. (2019) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3289600.3290990 · Cited by 7 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 9
- [19][19] Azin Ghazimatin, Rishiraj Saha Roy, and Gerhard Weikum. 2019. FAIRY: A Framework for Understanding Relationships between Users' Actions and their Social Feeds. In WSDM . -
- [22][22] Mohsen Jamali and Martin Ester. 2009. TrustWalker: A random walk model for combining trust-based and item-based recommendation. In KDD . -
- [35][35] Tim Miller, Rosina Weber, David Aha, and Daniele Magazzeni. 2019. IJCAI 2019 Workshop on Explainable AI (XAI). -
- [37][37] Athanasios N. Nikolakopoulos and George Karypis. 2019. Recwalk: Nearly uncoupled random walks for top-n recommendation. In WSDM . -
- [41][41] Joy Rimchala, Jineet Doshi, Qiang Zhu, Diane Chang, Nick Hoh, Conrad De Peuter, Shir Meir Lador, and Sambarta Dasgupta. 2019. KDD Workshop on Explainable AI for Fairness, Accountability, and Transparency. -
- [47][47] Hongwei Wang, Fuzheng Zhang, Jialin Wang, Miao Zhao, Wenjie Li, Xing Xie, and Minyi Guo. 2018. Ripplenet: Propagating user preferences on the knowledge graph for recommender systems. In CIKM . -
- [55][55] Chuxu Zhang, Ananthram Swami, and Nitesh Chawla. 2019. SHNE: Representation Learning for Semantic-Associated Heterogeneous Networks. In WSDM . -
- [57][57] Quanshi Zhang, Lixin Fan, Bolei Zhou, Sinisa Todorovic, Tianfu Wu, and Ying Nian Wu. 2019. CVPR-19 Workshop on Explainable AI. -
- [60][60] Yongfeng Zhang, Yi Zhang, Min Zhang, and Chirag Shah. 2019. EARS 2019: The 2nd International Workshop on ExplainAble Recommendation and Search. In SIGIR .
Cited by
Sorted by citations
Stepin, I., Alonso, J. M., Catala, A., & Pereira-Farina, M. (2021) · IEEE Access · doi:10.1109/access.2021.3051315 · Cited by 376 · see citing works
Chou, Y.-L., Moreira, C., Bruza, P., Ouyang, C., & Jorge, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.003 · Cited by 302 · see citing works
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Verma, S., Boonsanong, V., Hoang, M., Hines, K. E., Dickerson, J. P., & Shah, C. (2020) · arXiv · doi:10.48550/arxiv.2010.10596 · Cited by 267 · see citing works
Berrevoets, J., Kacprzyk, K., Qian, Z., & van der Schaar, M. (2023) · arXiv · doi:10.48550/arxiv.2303.02186 · Cited by 8 · see citing works
“…methods using a general multi-domain causal structure [23–25] Treatment effects Learn models that respect identification assumptions [26–39] Drug repurposing Relate multi-modal data using causal structure [40–44] Recommendation Infer causal effect of recommendation [45–49] Table 1: Real-world impact.”
BackgroundMethod
- Authors
- Ghazimatin, A., Balalau, O., Saha Roy, R., & Weikum, G.
- Affiliations
- Max Planck Institute for Informatics (DE)
- Institut national de recherche en sciences et technologies du numérique (FR)
- Max Planck Institute for Informatics, Saarbruecken, Germany
- Venue
- Proceedings of the 13th International Conference on Web Search and Data Mining
- Publisher
- ACM
- Published
- 2020-01-20
- Pages
- 196-204
- OpenAlex
- W2991380435
- Cited by
- 88
- References
- 65
- Citations by year
- 2026: 13 · 2025: 15 · 2024: 19 · 2023: 18 · 2022: 6 · 2021: 11 · 2020: 6
- FWCI
- 3.86
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM International Conference on Web Search and Data Mining (WSDM) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Funders
- DFG Collaborative Research Center 1223
- ERC Synergy Grant (imPACT) (610150)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- interpretable explanations, recommender systems, counterfactual explanations, user privacy, random walks, dynamic graphs, heterogeneous networks, user trust, explainable AI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
