staginSTAGIN: Spatio-Temporal Attention Graph Isomorphism Network
Stars: ✭ 34 (+54.55%)
awesome-efficient-gnnCode and resources on scalable and efficient Graph Neural Networks
Stars: ✭ 498 (+2163.64%)
ALPS 2021XAI Tutorial for the Explainable AI track in the ALPS winter school 2021
Stars: ✭ 55 (+150%)
GNNLens2Visualization tool for Graph Neural Networks
Stars: ✭ 155 (+604.55%)
adaptive-waveletsAdaptive, interpretable wavelets across domains (NeurIPS 2021)
Stars: ✭ 58 (+163.64%)
thermostatCollection of NLP model explanations and accompanying analysis tools
Stars: ✭ 126 (+472.73%)
3DInfomaxMaking self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.
Stars: ✭ 107 (+386.36%)
GraphMixCode for reproducing results in GraphMix paper
Stars: ✭ 64 (+190.91%)
fitFusion ICA Toolbox (MATLAB)
Stars: ✭ 13 (-40.91%)
NeuroVaultEasy to use web database for statistical maps.
Stars: ✭ 80 (+263.64%)
nltoolsPython toolbox for analyzing imaging data
Stars: ✭ 94 (+327.27%)
visualqcVisualQC : assistive tool to ease the quality control workflow of neuroimaging data.
Stars: ✭ 56 (+154.55%)
fmriflowsfmriflows is a consortium of many (dependent) fMRI analysis pipelines, including anatomical and functional pre-processing, univariate 1st and 2nd-level analysis, as well as multivariate pattern analysis.
Stars: ✭ 40 (+81.82%)
brainGraphGraph theory analysis of brain MRI data
Stars: ✭ 136 (+518.18%)
connectomemapper3Connectome Mapper 3 is a BIDS App that implements full anatomical, diffusion, resting/state functional MRI, and recently EEG processing pipelines, from raw T1 / DWI / BOLD , and preprocessed EEG data to multi-resolution brain parcellation with corresponding connection matrices.
Stars: ✭ 45 (+104.55%)
PyNetsA Reproducible Workflow for Structural and Functional Connectome Ensemble Learning
Stars: ✭ 114 (+418.18%)
ShapA game theoretic approach to explain the output of any machine learning model.
Stars: ✭ 14,917 (+67704.55%)
InterpretFit interpretable models. Explain blackbox machine learning.
Stars: ✭ 4,352 (+19681.82%)
removal-explanationsA lightweight implementation of removal-based explanations for ML models.
Stars: ✭ 46 (+109.09%)
CARLACARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Stars: ✭ 166 (+654.55%)
sageFor calculating global feature importance using Shapley values.
Stars: ✭ 129 (+486.36%)
zennitZennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Stars: ✭ 57 (+159.09%)
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (+113.64%)
contextual-aiContextual AI adds explainability to different stages of machine learning pipelines - data, training, and inference - thereby addressing the trust gap between such ML systems and their users. It does not refer to a specific algorithm or ML method — instead, it takes a human-centric view and approach to AI.
Stars: ✭ 81 (+268.18%)
deep-explanation-penalizationCode for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Stars: ✭ 110 (+400%)
mllpThe code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".
Stars: ✭ 15 (-31.82%)
responsible-ai-toolboxThis project provides responsible AI user interfaces for Fairlearn, interpret-community, and Error Analysis, as well as foundational building blocks that they rely on.
Stars: ✭ 615 (+2695.45%)
hierarchical-dnn-interpretationsUsing / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
Stars: ✭ 110 (+400%)
Transformer-MM-Explainability[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
Stars: ✭ 484 (+2100%)
ArenaRData generator for Arena - interactive XAI dashboard
Stars: ✭ 28 (+27.27%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (+86.36%)
GnnpapersMust-read papers on graph neural networks (GNN)
Stars: ✭ 12,293 (+55777.27%)
gnnTensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
Stars: ✭ 558 (+2436.36%)
mtad-gat-pytorchPyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).
Stars: ✭ 85 (+286.36%)
Meta-Fine-Tuning[CVPR 2020 VL3] The repository for meta fine-tuning in cross-domain few-shot learning.
Stars: ✭ 29 (+31.82%)
gemnet pytorchGemNet model in PyTorch, as proposed in "GemNet: Universal Directional Graph Neural Networks for Molecules" (NeurIPS 2021)
Stars: ✭ 80 (+263.64%)
GNNs-in-Network-NeuroscienceA review of papers proposing novel GNN methods with application to brain connectivity published in 2017-2020.
Stars: ✭ 92 (+318.18%)
VectorNetPytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”
Stars: ✭ 88 (+300%)
PDNThe official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Stars: ✭ 44 (+100%)
gnn-lspeSource code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
Stars: ✭ 165 (+650%)
GCLList of Publications in Graph Contrastive Learning
Stars: ✭ 25 (+13.64%)
gnn-re-rankingA real-time GNN-based method. Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
Stars: ✭ 64 (+190.91%)
GNN-Recommender-SystemsAn index of recommendation algorithms that are based on Graph Neural Networks.
Stars: ✭ 505 (+2195.45%)
BasicGNNTrackingThis shows a basic implementation of the global nearest neighbour (GNN) multi target Tracker. Kalman filter is used for Tracking and Auction Algorithm for determining the assignment of measurments to filters.
Stars: ✭ 36 (+63.64%)
BGCNA Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).
Stars: ✭ 129 (+486.36%)
dgcnnClean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).
Stars: ✭ 21 (-4.55%)
mmgnn textvqaA Pytorch implementation of CVPR 2020 paper: Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
Stars: ✭ 41 (+86.36%)
ncemLearning cell communication from spatial graphs of cells
Stars: ✭ 77 (+250%)
CausingCausing: CAUsal INterpretation using Graphs
Stars: ✭ 47 (+113.64%)
dtsA Keras library for multi-step time-series forecasting.
Stars: ✭ 130 (+490.91%)
D-TDNNPyTorch implementation of Densely Connected Time Delay Neural Network
Stars: ✭ 60 (+172.73%)
temporal-depth-segmentationSource code (train/test) accompanying the paper entitled "Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach" in CVPR 2019 (https://arxiv.org/abs/1903.10764).
Stars: ✭ 20 (-9.09%)