CS328 Introduction to Data Science - Prof. Anirban Dasgupta - Project: Sparsifying Networks while Preserving Properties

Sparsely Reconstructed Graphs (SpaRG) for robust and interpretable fMRI analysis using GNNs and VAEs.

Computationally characterizing Metal-Organic Frameworks (MOFs) via graph sparsification with Inverse Link Prediction using GCNs

The communication efficiency of federated learning is improved by sparsifying the parameters uploaded by the clients.

A simple C++14 and CUDA-based header-only library with tools for sparse-machine learning.

An implementation and report of the twice Ramanujan graph sparsifiers.

Simple Implementation of the CVPR 2024 Paper "JointSQ: Joint Sparsification-Quantization for Distributed Learning"

TensorFlow implementation of weight and unit pruning and sparsification

Feather is a module that enables effective sparsification of neural networks during training. This repository accompanies the paper "Feather: An Elegant Solution to Effective DNN Sparsification" (BMVC2023).

Sparsify Your Flux Models

TensorFlow implementation of weight and unit pruning and sparsification

(Unstructured) Weight Pruning via Adaptive Sparsity Loss

[CVPR 2023] Efficient Map Sparsification Based on 2D and 3D Discretized Grids

Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" proposed by Peking University and UC Berkeley.

Repository to track the progress in model compression and acceleration

Complex-valued neural networks for pytorch and Variational Dropout for real and complex layers.

A research library for pytorch-based neural network pruning, compression, and more.

Code for CRATE (Coding RAte reduction TransformEr).