MICCAI 2022 (Oral): Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis
-
Updated
Apr 29, 2023 - Python
#
interpretability-and-explainability
Here are 21 public repositories matching this topic...
[KDD'22] Source codes of "Graph Rationalization with Environment-based Augmentations"
graph-neural-networks rationalization molecular-property-prediction interpretability-and-explainability polymer-property-prediction
-
Updated
Mar 27, 2025 - Python
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation
pytorch data-augmentation generalization interpretability-and-explainability stable-diffusion icml-2023 spurious-correlation
-
Updated
Nov 17, 2025 - Python
Official code for the CVPR 2022 (oral) paper "OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks."
-
Updated
Apr 2, 2022 - Python
[ICCV 2023] Learning Support and Trivial Prototypes for Interpretable Image Classification
image-recognition fine-grained-classification interpretable-deep-learning interpretable-ai explainable-ai interpretable-neural-networks interpretability-and-explainability
-
Updated
Mar 27, 2025 - Python
[TPAMI 2025] Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
prototypical-networks game-theory-algorithms out-of-distribution-detection generative-modelling trustworthy-ai interpretability-and-explainability intepretable-machine-learning horse-racing-ai interpretable-image-recognition
-
Updated
May 25, 2025 - Python
Approximate Inverse Model Explanations (AIME): model-agnostic XAI through an approximate inverse operator.
python machine-learning python3 inverse-problems interpretability feature-importance explainable-ai xai model-agnostic xai-library model-agnostic-explanations interpretability-and-explainability aime-xai
-
Updated
Jul 20, 2026 - Python
hopwise: A Python Library for Explainable Recommendation based on Path Reasoning over Knowledge Graphs, ACM CIKM '25
recommender-systems link-prediction knowledge-graph-embeddings interpretability-and-explainability path-reasoning
-
Updated
Jul 15, 2026 - Python
TraceFL is a novel mechanism for Federated Learning that achieves interpretability by tracking neuron provenance. It identifies clients responsible for global model predictions, achieving 99% accuracy across diverse datasets (e.g., medical imaging) and neural networks (e.g., GPT).
testing debugging machine-learning software-engineering accountability differential-privacy interpretability federated-learning explainable-ai explainability interpretability-and-explainability
-
Updated
Nov 12, 2024 - Python
This repository contains the official code of the paper: "Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers", which is published in CVPR 2025.
interpretable-deep-learning interpretable-ai interpretable-ml explainable-ai explainable-ml interpretable-machine-learning interpretability-and-explainability
-
Updated
Aug 18, 2025 - Python
Layer-wise Semantic Dynamics (LSD) is a model-agnostic framework for hallucination detection in Large Language Models (LLMs). It analyzes the geometric evolution of hidden-state semantics across transformer layers, using contrastive alignment between model activations and ground-truth embeddings to detect factual drift and semantic inconsistency.
nlp machine-learning deep-learning pytorch representation-learning language-model-evaluation contrastive-learning trustworthy-ai large-language-models interpretability-and-explainability geometric-learning hallucination-detection hallucination-mitigation factuality-evaluation semantic-geometry transformer-analysis semantic-drift-analysis
-
Updated
Mar 12, 2026 - Python
Code for locating "critical neurons" in LLMs. We show that masking as few as 3 neurons can cripple a model's capabilities (ICLR 2026).
neural-networks ai-safety model-robustness interpretability-and-explainability llms mechanistic-interpretability iclr-2026 critical-neurons
-
Updated
Mar 27, 2026 - Python
Code implementation for our paper "Semi-supervised Concept Bottleneck Models" (ICCV-2025)
-
Updated
Jul 25, 2026 - Python
Explainable Speaker Recognition
forensics speaker-recognition resnet34 likelihood-ratio x-vector-pytorch interpretability-and-explainability automatic-voice-comparison forensic-speaker-recognition
-
Updated
Oct 26, 2022 - Python
An intepretable model for survival prediction in competing risks settings. Checkout our blog!! https://vectorinstitute.github.io/crisp-nam/blog/
-
Updated
Jul 21, 2026 - Python
[IROS 2026] TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks
deep-learning robotics navigation kan interpretability nuscenes semantic-kitti interpretability-and-explainability traversability traversability-estimation traversability-learning iros2026 eastpark
-
Updated
Jul 23, 2026 - Python
Visualization methods to interpret CNNs and Vision Transformers, trained in a supervised or self-supervised way. The methods are based on CAM or on the attention mechanism of Transformers. The results are evaluated qualitatively and quantitatively.
deep-neural-networks computer-vision transformers supervised-learning cnns explainable-ai self-supervised-learning interpretability-and-explainability
-
Updated
Jan 17, 2023 - Python
Implementation of the gradient-based t-SNE sttribution method described in our GLBIO oral presentation: 'Towards Computing Attributions for Dimensionality Reduction Techniques'
-
Updated
May 26, 2026 - Python
Counterfactual explanations for continuous reinforcement learning with simulation in T1D and Gym environments.
python reinforcement-learning openai-gym temporal-logic human-centered-ai interpretability-and-explainability counterfactual-explanation t1d-simulator
-
Updated
May 12, 2025 - Python
Standalone observability for agentic workflows. Conntrail wraps your agent's routing decisions, measures how stable they are under semantic perturbation of the input, classifies failures, and ships the records to a collector with a dashboard — without changing your agent's behavior.
-
Updated
Sep 3, 2026 - Python
Add this topic to your repo
To associate your repository with the interpretability-and-explainability topic, visit your repo's landing page and select "manage topics."