Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks

Räuker, Tilman, Ho, Anson, Casper, Stephen, Hadfield-Menell, Dylan·2023·2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
DOI 10.1109/satml54575.2023.00039

Cites (249)

Items 201–249 of 249

  1. ExSum: From Local Explanations to Model Understanding
    Yilun Zhou, Marco Túlio Ribeiro, Julie Shah · 2022 · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
  2. Picking BERT’s Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis
    Michael A. Lepori, Richard Thomas McCoy · 2020 · International Conference on Computational Linguistics
  3. Probing via Prompting
    Jiaoda Li, Ryan Cotterell, Mrinmaya Sachan · 2022 · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
  4. Explaining Deep Neural Networks using Unsupervised Clustering
    Yu-Han Liu, Sercan O. Arik · 2020 · arXiv.org
  5. 3DB: A Framework for Debugging Computer Vision Models
    Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai H. Vemprala, Logan Engstrom, Vibhav Vineet, Kai Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang et al. · 2021 · arXiv (Cornell University)
  6. On Saliency Maps and Adversarial Robustness
    Puneet Mangla, Vedant Singh, Vineeth Nallure Balasubramanian · 2021 · Lecture notes in computer science
  7. Similarity of Neural Networks with Gradients
    Shuai Tang, Wesley J. Maddox, Charlie Dickens, Tom Diethe, Andreas Damianou · 2020 · arXiv (Cornell University)
  8. Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
    Richard Meyes, Constantin Waubert de Puiseau, Andrés Felipe Posada-Moreno, Tobias Meisen · 2020 · arXiv (Cornell University)
  9. Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations
    Max Losch, Mario Fritz, Bernt Schiele · 2021 · International Journal of Computer Vision
  10. Protoformer: Embedding Prototypes for Transformers
    Ashkan Farhangi, Ning Sui, Nan Hua, Haiyan Bai, Arthur Huang, Zhishan Guo · 2022 · Lecture notes in computer science
  11. Deep Neural Model Inspection and Comparison via Functional Neuron Pathways
    James Fiacco, Samridhi Choudhary, Carolyn Penstein Rosé · 2019 · Proceedings of the conference - Association for Computational Linguistics. Meeting
  12. Interpreting Layered Neural Networks via Hierarchical Modular Representation
    Chihiro Watanabe · 2019 · Communications in computer and information science
  13. Transferred Discrepancy: Quantifying the Difference Between Representations
    Yunzhen Feng, Runtian Zhai, Di He, Liwei Wang, Bin Dong · 2020 · arXiv (Cornell University)
  14. Neural Execution Engines: Learning to Execute Subroutines
    Yujun Yan, Kevin Swersky, Danai Koutra, Parthasarathy Ranganathan, Milad Hashemi · 2020 · arXiv (Cornell University)
  15. LIREx: Augmenting Language Inference with Relevant Explanation
    Xinyan Zhao, V. G. Vinod Vydiswaran · 2020 · arXiv (Cornell University)
  16. Distilling Model Failures as Directions in Latent Space
    Saachi Jain, Lawrence, Hannah, Ankur Moitra · 2022 · arXiv (Cornell University)
  17. Methods for Pruning Deep Neural Networks
    Sunil Vadera, Salem Ameen · 2020 · arXiv (Cornell University)
  18. Probing Neural Dialog Models for Conversational Understanding
    Abdelrhman Saleh, Tovly Deutsch, Stephen Casper, Yonatan Belinkov, Stuart M. Shieber · 2020 · Workshop on NLP for Conversational AI (NLP4ConvAI)
  19. Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper)
    Yuhan Ji, Song Gao · 2023 · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)
  20. Second Order Optimization for Adversarial Robustness and Interpretability
    Theodoros Tsiligkaridis, Jay Roberts · 2020 · arXiv (Cornell University)
  21. ERIC: Extracting Relations Inferred from Convolutions
    Joe A Townsend, Theodoros Kasioumis, Hiroya Inakoshi · 2021 · Lecture notes in computer science
  22. CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
    Tuomas Oikarinen, Tsui-Wei Weng · 2022 · arXiv (Cornell University)
  23. Robust Feature-Level Adversaries are Interpretability Tools
    Casper, Stephen, Max Nadeau, Dylan Hadfield-Menell · 2021 · arXiv (Cornell University)
  24. Explaining Neural Networks by Decoding Layer Activations
    Johannes Schneider, Michail Vlachos · 2021 · Lecture notes in computer science
  25. Exploring the Interchangeability of CNN Embedding Spaces
    David G. McNeely-White, Benjamin Sattelberg, Nathaniel Blanchard, Beveridge, Ross · 2020 · arXiv (Cornell University)
  26. Attribution-based Explanations that Provide Recourse Cannot be Robust
    Hidde Fokkema, Rianne de Heide, Tim van Erven · 2022 · arXiv (Cornell University)
  27. Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior
    Jean-Stanislas Denain, Jacob Steinhardt · 2022 · arXiv (Cornell University)
  28. Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning
    Olivia Wiles, Isabela Albuquerque, Sven Gowal · 2022 · arXiv (Cornell University)
  29. An Effective Hit-or-Miss Layer Favoring Feature Interpretation as Learned Prototypes Deformations
    Adrien Deliège, Anthony Cioppa, Marc Van Droogenbroeck · 2019 · arXiv (Cornell University)
  30. Weight Banding
    Michael Petrov, Chelsea Voss, Ludwig Schubert · 2021 · Distill
  31. On the Symmetries of Deep Learning Models and their Internal Representations
    Charles Godfrey, Brown, Davis, Tegan Emerson · 2022 · arXiv (Cornell University)
  32. Identifiable Variational Autoencoders via Sparse Decoding.
    Gemma E. Moran, Dhanya Sridhar, Zhaoran Wang · 2021 · arXiv (Cornell University)
  33. Exploring Linear Feature Disentanglement for Neural Networks
    Tiantian He, Zhibin Li, Yongshun Gong, Yazhou Yao, Xiushan Nie, Yilong Yin · 2022 · IEEE International Conference on Multimedia and Expo (ICME)
  34. Clustering units in neural networks: upstream vs downstream information
    Richard D. Lange, David Rolnick, Konrad Paul Kording · 2022 · arXiv (Cornell University)
  35. Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks
    Casper, Stephen, Kaivalya Hariharan, Dylan Hadfield-Menell · 2022 · arXiv (Cornell University)
  36. Generating Post-Hoc Rationales of Deep Visual Classification Decisions
    Zeynep Akata, Lisa Anne Hendricks, Stephan Alaniz, Trevor Darrell · 2018 · The Springer series on challenges in machine learning
  37. Explanatory Graphs for CNNs
    Quanshi Zhang, Xin Wang, Ruiming Cao, Ying Nian Wu, Shi, Feng, Song Chun Zhu · 2018 · arXiv (Cornell University)
  38. Dissecting Pruned Neural Networks
    Jonathan Frankle, David Bau · 2019 · arXiv (Cornell University)
  39. Representation Transfer by Optimal Transport
    Xuhong Li, Yves Grandvalet, Rémi Flamary · 2020 · arXiv (Cornell University)
  40. Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards
    Marco Valentino, Ian E. Pratt-Hartmann, André Freitas · 2021 · arXiv (Cornell University)
  41. Toward a Unified Framework for Debugging Gray-box Models.
    Andrea Bontempelli, Fausto Giunchiglia, Andrea Passerini, Stefano Teso · 2021 · Iris (University of Trento)
  42. TopKConv: Increased Adversarial Robustness Through Deeper Interpretability
    Henry Eigen, Amir Sadovnik · 2021 · IEEE International Conference on Machine Learning and Applications (ICMLA)
  43. Deconfounded Representation Similarity for Comparison of Neural Networks
    Tianyu Cui, Yogesh Kumar, Pekka Marttinen · 2022 · Aaltodoc (Aalto University)
  44. Towards Benchmarking Explainable Artificial Intelligence Methods
    Lars Holmberg · 2022 · arXiv (Cornell University)
  45. Extreme sparsity gives rise to functional specialization.
    Gabriel Béna, Dan F. M. Goodman · 2021 · arXiv (Cornell University)
  46. Fighting Adversarial Images With Interpretable Gradients
    Keke Du, Shan Chang, Huixiang Wen · 2021 · ACM Turing Award Celebration Conference - China (ACM TURC)
  47. On the Robustness of Explanations of Deep Neural Network Models: A Survey
    Amlan Jyoti, Karthik Balaji Ganesh, Manoj Gayala · 2022 · arXiv (Cornell University)
  48. Probing Tasks Under Pressure
    Alessio Miaschi, Chiara Alzetta, Dominique Brunato⋄, Felice Dell’Orletta⋄, Giulia Venturi⋄ · 2022 · Accademia University Press eBooks
  49. Quantifying Local Specialization in Deep Neural Networks
    Shlomi Hod, Daniel Filan, Casper, Stephen · 2021 · arXiv (Cornell University)