71 skills found · Page 1 of 3
marcoancona / DeepExplainA unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
TryCatchHCF / PacketWhisperPacketWhisper: Stealthily exfiltrate data and defeat attribution using DNS queries and text-based steganography. Avoid the problems associated with typical DNS exfiltration methods. Transfer data between systems without the communicating devices directly connecting to each other or to a common endpoint. No need to control a DNS Name Server.
inseq-team / InseqInterpretability for sequence generation models 🐛 🔍
BranchMetrics / Web Branch Deep Linking AttributionThe Branch Web SDK for deep linking and attribution. Once initialized, the Branch Web SDK allows you to create and share links with a banner (web only), over SMS, or your own methods by generating deep links. It also offers event tracking, access to referrals, and management of credits.
chr5tphr / ZennitZennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
MadryLab / TrakA fast, effective data attribution method for neural networks in PyTorch
yulongwang12 / Visual AttributionPytorch Implementation of recent visual attribution methods for model interpretability
Julia-XAI / ExplainableAI.jlExplainable AI in Julia.
anthropics / Attribution Graphs Frontendhttps://transformer-circuits.pub/2025/attribution-graphs/methods.html
Wuyxin / ReFineTowards Multi-Grained Explainability for Graph Neural Networks (NeurIPS 2021) + Pytorch Implementation of GNN attribution methods
dilyabareeva / QuandaA toolkit for quantitative evaluation of data attribution methods.
Piyushi-0 / ACECode for our ICML '19 oral paper: Neural Network Attributions: A Causal Perspective.
ypeiyu / Attribution Recalibration[ICLR 2023 Spotlight] Re-calibrating Feature Attributions for Model Interpretation
riverback / Pytorch AttributionAttribution methods that explain image classification models, implemented in PyTorch, and support batch inputs and GPU.
ianchute / Shapley Attribution Model Zhao NaiveA Python implementation of "Shapley Value Methods for Attribution Modeling in Online Advertising" by Zhao, et al.
matlab-deep-learning / Explore Deep Network Explainability Using An AppThis repository provides an app for exploring the predictions of an image classification network using several deep learning visualization techniques. Using the app, you can: explore network predictions with occlusion sensitivity, Grad-CAM, and gradient attribution methods, investigate misclassifications using confusion and t-SNE plots, visualize layer activations, and many more techniques to help you understand and explain your deep network’s predictions.
erfanhatefi / Pruning By EXplaining In PyTorchPruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers, Paper accepted at eXCV workshop of ECCV 2024
frankaging / BERT LRPOn Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification
eleafeit / Ad Response TutorialThis tutorial shows users how to evaluate advertising response using last click attribution, experiments, marketing mix models and attribution models. By applying these methods to the same (synthetic) data set, users will learn how the methods compare. We also illustrate the data manipulation that is required to prepare typical raw advertising data for analysis. Examples are worked in R and slides are provided in LaTeX.
CVxTz / IntegratedGradientsPytorchIntegrated gradients attribution method implemented in PyTorch
