pku-ml Goto Github PK

adainf

Official code for ICLR 2024 paper Do Generated Data Always Help Contrastive Learning?

advnotrealfeatures

Official Code for reproductivity of the NeurIPS 2023 paper: Adversarial Examples Are Not Real Features

arc

Official Code for ICLR2022 Paper: Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

architecturemattersgcl

Official code for NeurIPS 2023 "Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning"

at-for-ood

Official code for NeurIPS 2022 paper "Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors"

cfa

clip-help-simclr

Official Code for ICML 2023 Paper: On the Generalization of Multi-modal Contrastive Learning

clustermim

Official Code for ICLR 2024 Paper: On the Role of Discrete Tokenization in Visual Representation Learning

contranorm

Official code for ICLR 2023 paper "ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond "

dgc

Official Code of Decoupled Graph Convolution (DGC)

diffusion-pid-protection

dynacl

[ICLR 2023] Official repository of the paper "Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning"

generalist

CVPR 2023 generalist

laplaciancanonization

Official code for NeurIPS 2023 paper "Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding".

lookaheadlookaround

message-passing-contrastive-learning

Official Code for ICLR 2023 Paper: A Message Passing Perspective on Learning Dynamics of Contrastive Learning

nlb

Official Code for reproductivity of the ICLR Workshop DPFM 2024 paper: How to Craft Backdoors with Unlabeled Data Alone?

non_neg

Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning

rank-differential-mechanism

Official code for ICLR 2023 paper "Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism"

rebat

Official PyTorch implementation of ReBAT (ReBalanced Adversarial Training) in NeurIPS 2023 "Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective".

repgan

Official code of REPGAN (Reparameterized Sampling for Generative Adversarial Networks)

self-ensemble-adversarial-training

SEAT

tmllib

A Trustworthy Machine Learning Algorithm Library

tri-factor-contrastive-learning

Official Code for NeurIPS 2023 Paper: Identifiable Contrastive Learning with Automatic Feature Importance Discovery

u-mae

Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders

when-adversarial-training-meets-vision-transformers

Official implementation of "When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture" published at NeurIPS 2022.