twistedcubic / attention-rank-collapse
[ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
☆164Updated 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
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆104Updated 3 years ago
- Awesome Contrastive Learning for CV & NLP☆162Updated 3 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆118Updated 3 years ago
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆190Updated 2 years ago
- NeurIPS 2020, Debiased Contrastive Learning☆283Updated 2 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆152Updated last year
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 3 years ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆262Updated 3 years ago
- [ICML 2020] code for the flooding regularizer proposed in "Do We Need Zero Training Loss After Achieving Zero Training Error?"☆91Updated 2 years ago
- Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…☆251Updated 3 years ago
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆115Updated 4 years ago
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆119Updated 3 years ago
- Code to reproduce the results for Compositional Attention☆60Updated 2 years ago
- MoCo with Alignment and Uniformity Loss.☆62Updated 3 years ago
- ☆81Updated 8 months ago
- PyTorch implementation of a Variational Autoencoder with Gumbel-Softmax Distribution☆208Updated 6 years ago
- pytorch implementation of VAE-Gumble-Softmax☆62Updated 4 years ago
- Fully featured implementation of Routing Transformer☆291Updated 3 years ago
- ICLR 2021, Contrastive Learning with Hard Negative Samples☆265Updated 3 years ago
- LEARNING LATENT PERMUTATIONS WITH GUMBEL-SINKHORN NETWORKS IMPLEMENTATION WITH PYTORCH☆79Updated last year
- Crawl & visualize ICLR papers and reviews.☆107Updated 3 years ago
- Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2…☆441Updated 2 years ago
- Variational Transformers for Diverse Response Generation☆81Updated 9 months ago
- Understanding Training Dynamics of Deep ReLU Networks☆289Updated 2 months ago
- Implementation of OmniNet, Omnidirectional Representations from Transformers, in Pytorch☆57Updated 4 years ago
- Learning to Encode Position for Transformer with Continuous Dynamical Model☆59Updated 4 years ago
- code for paper "Graph Structure of Neural Networks"☆155Updated 3 years ago
- Implementation of Sparsemax activation in Pytorch☆159Updated 4 years ago
- Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)☆103Updated 3 years ago
- code for Explicit Sparse Transformer☆60Updated last year