CoChat
Sign Up
Cited by 9Explainable Artificial Intelligence (XAI)Logic, Reasoning, and KnowledgeAdvanced Neural Network Applications

The DOI matches its Crossref record.

Self-Explaining Deep Models with Logic Rule Reasoning

Open access
Lee, Seungeon, Wang, Xiting, Han, Sungwon, Yi, Xiaoyuan, Xie, Xing, Cha, Meeyoung·2022·Advances in Neural Information Processing Systems 35
DOI 10.52202/068431-0232
Open this paper in CoChat — free accountOpen PDF

Abstract

We present SELOR, a framework for integrating self-explaining capabilities into a given deep model to achieve both high prediction performance and human precision. By "human precision", we refer to the degree to which humans agree with the reasons models provide for their predictions. Human precision affects user trust and allows users to collaborate closely with the model. We demonstrate that logic rule explanations naturally satisfy human precision with the expressive power required for good predictive performance. We then illustrate how to enable a deep model to predict and explain with logic rules. Our method does not require predefined logic rule sets or human annotations and can be learned efficiently and easily with widely-used deep learning modules in a differentiable way. Extensive experiments show that our method gives explanations closer to human decision logic than other methods while maintaining the performance of deep learning models.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.52202/068431-0232

Cites

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Most recommender systems are black boxes whose inner workings are inscrutable to human understanding, diminishing user trust.

    “This is crucial as most recommender systems are black boxes whose inner workings are inscrutable to human understanding [126], diminishing user trust.”

    From When large language models meet personalization: perspectives of challenges and opportunities (2024) · cites this paper as [126]

    The Introduction (p. 1) says deep models have obscured inner workings and raises questions about their trustworthiness. The discussion on p. 2 says unreasonable explanations can hamper user trust. The paper does not establish that most recommender systems are black boxes; recommender systems appear only in a cited reference (p. 11). (LLM, conf=0.85)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 42

  1. [1][1] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. "Why Should I Trust You?" explaining the predictions of any classifier. In KDD , 2016. -
  2. [2][2] Sebastian Thrun. Extracting rules from artificial neural networks with distributed representations. In NeurIPS , 1994. -
  3. [4][4] Tao Lei, Regina Barzilay, and Tommi Jaakkola. Rationalizing neural predictions. In EMNLP , 2016. -
  4. [5][5] Dimitrios Alikaniotis, Helen Yannakoudakis, and Marek Rei. Automatic text scoring using neural networks. In ACL , 2016. -
  5. [6][6] Hendrik Strobelt, Sebastian Gehrmann, Hanspeter Pfister, and Alexander M Rush. Lstmvis: A tool for visual analysis of hidden state dynamics in recurrent neural networks. IEEE TVCG , 2017. -
  6. [7][7] WJames Murdoch, Peter J Liu, and Bin Yu. Beyond word importance: Contextual decomposition to extract interactions from lstms. In ICLR , 2018. -
  7. [8][8] Georgina Peake and Jun Wang. Explanation mining: Post hoc interpretability of latent factor models for recommendation systems. In KDD , 2018. -
  8. [9][9] Jian Liang, Bing Bai, Yuren Cao, Kun Bai, and Fei Wang. Adversarial infidelity learning for model interpretation. In KDD , 2020. -
  9. [10][10] Jingyue Gao, Xiting Wang, Yasha Wang, Yulan Yan, and Xing Xie. Learning groupwise explanations for black-box models. In IJCAI , 2021. -
  10. [11][11] David Alvarez Melis and Tommi Jaakkola. Towards robust interpretability with self-explaining neural networks. In NeurIPS , 2018. -
  11. [13][13] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In NeurIPS , 2017. -
  12. [14][14] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Anchors: High-precision modelagnostic explanations. In AAAI , 2018. -
  13. [15][15] Chaoyu Guan, Xiting Wang, Quanshi Zhang, Runjin Chen, Di He, and Xing Xie. Towards a deep and unified understanding of deep neural models in nlp. In ICML , 2019. -
  14. [18][18] Hongyu Yang, Cynthia Rudin, and Margo Seltzer. Scalable bayesian rule lists. In ICML , 2017. -
  15. [19][19] Richard Evans and Edward Grefenstette. Learning explanatory rules from noisy data. Journal of Artificial Intelligence Research , 2018. -
  16. [20][20] Elaine Angelino, Nicholas Larus-Stone, Daniel Alabi, Margo Seltzer, and Cynthia Rudin. Learning certifiably optimal rule lists. In KDD , 2017. -
  17. [21][21] Yao Ming, Panpan Xu, Huamin Qu, and Liu Ren. Interpretable and steerable sequence learning via prototypes. In KDD , 2019. -
  18. [22][22] Zhongxia Chen, Xiting Wang, Xing Xie, Mehul Parsana, Akshay Soni, Xiang Ao, and Enhong Chen. Towards explainable conversational recommendation. In IJCAI , 2020. -
  19. [25][25] Piyawat Lertvittayakumjorn, Lucia Specia, and Francesca Toni. Find: Human-in-the-loop debugging deep text classifiers. In EMNLP , 2020. -
  20. [26][26] Gabriele Ciravegna, Francesco Giannini, Marco Gori, Marco Maggini, and Stefano Melacci. Human-driven fol explanations of deep learning. In IJCAI , 2021. -
  21. [27][27] Wolfgang Stammer, Patrick Schramowski, and Kristian Kersting. Right for the right concept: Revising neuro-symbolic concepts by interacting with their explanations. In CVPR , 2021. -
  22. [28][28] Andrea Bontempelli, Fausto Giunchiglia, Andrea Passerini, and Stefano Teso. Toward a unified framework for debugging gray-box models. arXiv preprint arXiv:2109.11160 , 2021. - · arXiv
  23. [29][29] Luc De Raedt, Sebastijan Dumancic, Robin Manhaeve, and Giuseppe Marra. From statistical relational to neuro-symbolic artificial intelligence. In IJCAI , 2020. -
  24. [30][30] Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton, and Swarat Chaudhuri. Houdini: lifelong learning as program synthesis. In NeurIPS , 2018. -
  25. [31][31] Kevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama, and Josh Tenenbaum. Learning libraries of subroutines for neurally-guided bayesian program induction. In NeurIPS , 2018. -
  26. [32][32] Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, and Sumit Gulwani. Neural-guided deductive search for real-time program synthesis from examples. In ICLR , 2018. -
  27. [33][33] Kevin Ellis, Daniel Ritchie, Armando Solar-Lezama, and Josh Tenenbaum. Learning to infer graphics programs from hand-drawn images. In NeurIPS , 2018. -
  28. [34][34] Jiayuan Mao, Chuang Gan, Pushmeet Kohli, Joshua B Tenenbaum, and Jiajun Wu. The neurosymbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. In ICLR , 2019. -
  29. [35][35] Dongran Yu, Bo Yang, Qianhao Wei, Anchen Li, and Shirui Pan. A probabilistic graphical model based on neural-symbolic reasoning for visual relationship detection. In CVPR , 2022. -
  30. [37][37] Fan Yang, Zhilin Yang, and William W Cohen. Differentiable learning of logical rules for knowledge base reasoning. In NeurIPS , 2017. -
  31. [38][38] Kangzhi Zhao, Xiting Wang, Yuren Zhang, Li Zhao, Zheng Liu, Chunxiao Xing, and Xing Xie. Leveraging demonstrations for reinforcement recommendation reasoning over knowledge graphs. In SIGIR , 2020. -
  32. [39][39] Yuzuru Okajima and Kunihiko Sadamasa. Deep neural networks constrained by decision rules. In AAAI , 2019. -
  33. [41][41] Alex Kendall, Yarin Gal, and Roberto Cipolla. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In CVPR , 2018. -
  34. [43][43] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS , 2017. -
  35. [44][44] Xiang Zhang, Junbo Zhao, and Yann LeCun. Character-level convolutional networks for text classification. In NeurIPS , 2015. -
  36. [47][47] Takaya Saito and Marc Rehmsmeier. The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets. PloS one , 10(3):e0118432, 2015. -
  37. [48][48] Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL , 2019. -
  38. [49][49] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 , 2019. - · arXiv
  39. [50][50] Junnan Li, Richard Socher, and Steven CH Hoi. Dividemix: Learning with noisy labels as semi-supervised learning. In ICLR , 2019. -
  40. [51][51] Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. Mixup: Beyond empirical risk minimization. In ICLR , 2018. -
  41. [53][53] Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In ICML , 2018. -
  42. [54][54] Eyal Peer, David Rothschild, Andrew Gordon, Zak Evernden, and Ekaterina Damer. Data quality of platforms and panels for online behavioral research. Behavior Research Methods , 54(4):1643-1662, 2022. -

Cited by

Sorted by citations

Metadata

Authors
Lee, S., Wang, X., Han, S., Yi, X., Xie, X., & Cha, M.
ORCID
Venue
Advances in Neural Information Processing Systems 35
Publisher
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
Published
2022
Pages
3203-3216
ISSN
1049-5258 (ISSN-L)
DOI
10.52202/068431-0232
OpenAlex
W7133210228
Cited by
9
References
0
Citations by year
2026: 2 · 2025: 1 · 2024: 3 · 2023: 2 · 2022: 1
FWCI
0.91
Type
conference paper
Language
en
Open access
Locations
  • neural information processing systems (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Microsoft Research
  • Institute for Basic Science (IBS-R029-C2)
  • Ministry of Science and ICT, South Korea
  • Microsoft Research Asia
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
deep learning interpretability, 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