{"total":221,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140,"area":null},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79,"area":null},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"area":null},{"id":"2210.07147","title":"Global Explainability of GNNs via Logic Combination of Learned Concepts","created":"2022-10-13","cited_by_count":65,"area":null},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59,"area":null},{"id":"2105.10278","title":"On Explaining Random Forests with SAT","created":"2021-05-21","cited_by_count":57,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"area":null},{"id":"2402.13055","title":"Identifying Semantic Induction Heads to Understand In-Context Learning","created":"2024-02-20","cited_by_count":47,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"area":null},{"id":"2106.00305","title":"Independent Prototype Propagation for Zero-Shot Compositionality","created":"2021-06-01","cited_by_count":42,"area":null},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2301.12276","title":"ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts","created":"2023-01-28","cited_by_count":33,"area":null},{"id":"2305.07348","title":"A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects","created":"2023-05-12","cited_by_count":30,"area":null},{"id":"2210.16966","title":"Interpretable Geometric Deep Learning via Learnable Randomness Injection","created":"2022-10-30","cited_by_count":27,"area":null},{"id":"2308.08162","title":"Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations","created":"2023-08-16","cited_by_count":27,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24,"area":null},{"id":"2303.07811","title":"ICICLE: Interpretable Class Incremental Continual Learning","created":"2023-03-14","cited_by_count":24,"area":null},{"id":"2108.10612","title":"ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification","created":"2021-08-24","cited_by_count":22,"area":null},{"id":"2309.07742","title":"Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning","created":"2023-09-14","cited_by_count":22,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2204.01208","title":"Attribute Prototype Network for Any-Shot Learning","created":"2022-04-04","cited_by_count":19,"area":null},{"id":"2306.12330","title":"ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data","created":"2023-06-21","cited_by_count":18,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2410.02331","title":"Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2406.16708","title":"CausalFormer: An Interpretable Transformer for Temporal Causal Discovery","created":"2024-06-24","cited_by_count":17,"area":null},{"id":"2407.15527","title":"Interpretable Concept-Based Memory Reasoning","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2210.01784","title":"COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation","created":"2022-10-04","cited_by_count":15,"area":null},{"id":"2405.14331","title":"LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2504.19774","title":"If Concept Bottlenecks are the Question, are Foundation Models the Answer?","created":"2025-04-28","cited_by_count":15,"area":null},{"id":"2210.01974","title":"Towards Prototype-Based Self-Explainable Graph Neural Network","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2502.11245","title":"Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens","created":"2025-02-16","cited_by_count":13,"area":null},{"id":"2503.01087","title":"Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2108.13828","title":"PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs","created":"2021-08-31","cited_by_count":12,"area":null},{"id":"2212.07425","title":"Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments","created":"2022-12-12","cited_by_count":12,"area":null},{"id":"2212.08733","title":"Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2101.03919","title":"Comprehensible Convolutional Neural Networks via Guided Concept Learning","created":"2021-01-11","cited_by_count":11,"area":null},{"id":"2204.04601","title":"Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention","created":"2022-04-10","cited_by_count":11,"area":null},{"id":"2310.06966","title":"On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis","created":"2023-10-10","cited_by_count":11,"area":null},{"id":"2406.14675","title":"This Looks Better than That: Better Interpretable Models with ProtoPNeXt","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2103.00752","title":"Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2109.05800","title":"DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2211.13638","title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes","created":"2022-11-24","cited_by_count":10,"area":null},{"id":"2401.01549","title":"Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction","created":"2024-01-03","cited_by_count":10,"area":null},{"id":"2404.10420","title":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","created":"2024-04-16","cited_by_count":10,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2211.04110","title":"Privacy Meets Explainability: A Comprehensive Impact Benchmark","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2309.02401","title":"Prototype-based Dataset Comparison","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2102.05298","title":"Inductive Granger Causal Modeling for Multivariate Time Series","created":"2021-02-10","cited_by_count":8,"area":null},{"id":"2205.09901","title":"Cardinality-Minimal Explanations for Monotonic Neural Networks","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2208.00457","title":"INSightR-Net: Interpretable Neural Network for Regression using Similarity-based Comparisons to Prototypical Examples","created":"2022-07-31","cited_by_count":8,"area":null},{"id":"2402.02754","title":"Focal Modulation Networks for Interpretable Sound Classification","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2103.02768","title":"Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction","created":"2021-03-04","cited_by_count":7,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2203.04109","title":"Explaining Classifiers by Constructing Familiar Concepts","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2311.15438","title":"ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]","created":"2023-11-26","cited_by_count":7,"area":null},{"id":"2106.09636","title":"Multi-Stage Prototype Learning for Interpretable Time Series Classification","created":"2021-06-17","cited_by_count":6,"area":null},{"id":"2204.08554","title":"CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2310.15741","title":"Interpretable Medical Image Classification using Prototype Learning and Privileged Information","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2312.07822","title":"Prototypical Self-Explainable Models Without Re-training","created":"2023-12-13","cited_by_count":6,"area":null},{"id":"2404.00673","title":"A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures","created":"2024-03-31","cited_by_count":6,"area":null},{"id":"2104.06982","title":"To Trust or Not to Trust a Regressor: Estimating and Explaining Trustworthiness of Regression Predictions","created":"2021-04-14","cited_by_count":5,"area":null},{"id":"2205.11433","title":"Informed Pre-Training on Prior Knowledge","created":"2022-05-23","cited_by_count":5,"area":null},{"id":"2212.09062","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","created":"2022-12-18","cited_by_count":5,"area":null},{"id":"2301.00436","title":"Hierarchical Explanations for Video Action Recognition","created":"2023-01-01","cited_by_count":5,"area":null},{"id":"2305.07132","title":"Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2307.04343","title":"Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2308.05411","title":"Explainable AI applications in the Medical Domain: a systematic review","created":"2023-08-10","cited_by_count":5,"area":null},{"id":"2309.11155","title":"ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinement","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2312.10977","title":"Predict and Interpret Health Risk using EHR through Typical Patients","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2402.09318","title":"Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2407.19683","title":"Revisiting the robustness of post-hoc interpretability methods","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2410.08925","title":"An Overview of Prototype Formulations for Interpretable Deep Learning","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2412.03761","title":"Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks","created":"2024-12-04","cited_by_count":5,"area":null},{"id":"2412.18529","title":"Accelerating process control and optimization via machine learning: A review","created":"2024-12-24","cited_by_count":5,"area":null},{"id":"2109.11160","title":"Toward a Unified Framework for Debugging Concept-based Models","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2205.13997","title":"Prototype Based Classification from Hierarchy to Fairness","created":"2022-05-27","cited_by_count":4,"area":null},{"id":"2211.12173","title":"Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models","created":"2022-11-22","cited_by_count":4,"area":null},{"id":"2212.03396","title":"Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling","created":"2022-12-07","cited_by_count":4,"area":null},{"id":"2302.01416","title":"Neural Insights for Digital Marketing Content Design","created":"2023-02-02","cited_by_count":4,"area":null}],"next_cursor":"100"}