twistedcubic / attention-rank-collapseLinks
[ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
☆166Updated 4 years ago
Alternatives and similar repositories for attention-rank-collapse
Users that are interested in attention-rank-collapse are comparing it to the libraries listed below
Sorting:
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆120Updated 4 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆228Updated 3 years ago
- [ICML 2020] code for the flooding regularizer proposed in "Do We Need Zero Training Loss After Achieving Zero Training Error?"☆94Updated 2 years ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆268Updated 4 years ago
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆196Updated 2 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆108Updated 4 years ago
- Awesome Contrastive Learning for CV & NLP☆165Updated 4 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆151Updated 2 years ago
- Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization☆182Updated 3 years ago
- Fully featured implementation of Routing Transformer☆296Updated 4 years ago
- NeurIPS 2020, Debiased Contrastive Learning☆283Updated 2 years ago
- Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2…☆458Updated 3 years ago
- ☆81Updated last year
- Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch☆70Updated 5 years ago
- Learning to Encode Position for Transformer with Continuous Dynamical Model☆59Updated 5 years ago
- Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]☆86Updated last year
- Loss and accuracy go opposite ways...right?☆95Updated 5 years ago
- Implementation of Sparsemax activation in Pytorch☆166Updated 5 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆120Updated 4 years ago
- Understanding Training Dynamics of Deep ReLU Networks☆302Updated 3 weeks ago
- ☆84Updated 4 years ago
- Code to reproduce the results for Compositional Attention☆59Updated 2 years ago
- Crawl & visualize ICLR papers and reviews.☆107Updated 3 years ago
- PyTorch implementation of a Variational Autoencoder with Gumbel-Softmax Distribution☆211Updated 7 years ago
- Code for Which Tasks Should Be Learned Together in Multi-task Learning?☆98Updated 2 years ago
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆124Updated 5 years ago
- Implementation of OmniNet, Omnidirectional Representations from Transformers, in Pytorch☆59Updated 4 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆144Updated 3 years ago
- Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)☆201Updated 2 years ago
- A Pytorch implementation of the optimal transport kernel embedding☆118Updated 4 years ago