twistedcubic / attention-rank-collapseLinks
[ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
☆169Updated 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 the flooding regularizer proposed in "Do We Need Zero Training Loss After Achieving Zero Training Error?"☆95Updated 3 years ago
- [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
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆269Updated 4 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆111Updated 4 years ago
- Awesome Contrastive Learning for CV & NLP☆165Updated 4 years ago
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆196Updated 3 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆153Updated 2 years ago
- Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization☆182Updated 4 years ago
- NeurIPS 2020, Debiased Contrastive Learning☆285Updated 2 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆120Updated 4 years ago
- ☆81Updated last year
- Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch☆70Updated 5 years ago
- ☆84Updated 4 years ago
- Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)☆202Updated 3 years ago
- Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2…☆459Updated 3 years ago
- Understanding Training Dynamics of Deep ReLU Networks☆305Updated 2 months ago
- Fully featured implementation of Routing Transformer☆299Updated 4 years ago
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆126Updated 5 years ago
- A pytorch &keras implementation and demo of Fastformer.☆191Updated 3 years ago
- Implementation of Sparsemax activation in Pytorch☆166Updated 5 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
- Code used in "Understanding Dimensional Collapse in Contrastive Self-supervised Learning" paper.☆79Updated 3 years ago
- Learning to Encode Position for Transformer with Continuous Dynamical Model☆59Updated 5 years ago
- Official Pytorch's implementation of RotoGrad☆80Updated 2 years ago
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning☆114Updated 4 years ago
- Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]☆86Updated last year
- Code to reproduce the results for Compositional Attention☆59Updated 3 years ago
- code for paper "Graph Structure of Neural Networks"☆156Updated 4 years ago
- ☆34Updated last year