paper-with-me

Papers

Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers

2020-06-05 · Krzysztof Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Davis, David Belanger, Lucy Colwell, Adrian Weller

Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dependencies between distant inputs continues to grow. In response, solutions that exploit the structure and sparsity of the learned attention matrix have blossomed. However, real-world applications that involve long sequences, such as biological sequence analysis, may fall short of meeting these assumptions, precluding exploration of these models. To address this challenge, we present a new Transformer architecture, Performer, based on Fast Attention Via Orthogonal Random features (FAVOR). Our mechanism scales linearly rather than quadratically in the number of tokens in the sequence, is characterized by sub-quadratic space complexity and does not incorporate any sparsity pattern priors. Furthermore, it provides strong theoretical guarantees: unbiased estimation of the attention matrix and uniform convergence. It is also backwards-compatible with pre-trained regular Transformers. We demonstrate its effectiveness on the challenging task of protein sequence modeling and provide detailed theoretical analysis.

📄 PDF Abstract BibTeX arXiv:2006.03555

Code (1)

google-research/google-research 공식 구현 tf

Tasks

Language ModelingLanguage ModellingMasked Language Modeling

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Viral Proteins Reveal Geometry of Protein Language Models

2026-06-10 · Arthur Bigot, Harmon Bhasin, Core Francisco Park, Eugene Shakhnovich 외 arxiv

Protein language models are trained on highly imbalanced datasets, raising the question of how they represent underrepresented biological sequences. Using viral proteins as a case study across ESM model families, we iden…

Protein Language Model

MeMDLM: De Novo Membrane Protein Design with Masked Discrete Diffusion Protein Language Models

2024-10-22 · Shrey Goel, Vishrut Thoutam, Edgar Mariano Marroquin, Aaron Gokaslan 외

Masked Diffusion Language Models (MDLMs) have recently emerged as a strong class of generative models, paralleling state-of-the-art (SOTA) autoregressive (AR) performance across natural language modeling domains. While t…

Language ModelingLanguage ModellingProtein Design

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

2024-10-10 · Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Zachary Quinn 외

Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences. However, application domains need to e…

Denoising

Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers

2024-10-29 · Yingheng Wang, Zichen Wang, Gil Sadeh, Luca Zancato 외

Self-supervised training of language models (LMs) has seen great success for protein sequences in learning meaningful representations and for generative drug design. Most protein LMs are based on the Transformer architec…

Drug DesignLanguage ModelingLanguage ModellingMamba+4

Dynamic Masking Rate Schedules for MLM Pretraining

2023-05-24 · Zachary Ankner, Naomi Saphra, Davis Blalock, Jonathan Frankle 외

Most works on transformers trained with the Masked Language Modeling (MLM) objective use the original BERT model's fixed masking rate of 15%. We propose to instead dynamically schedule the masking rate throughout trainin…

Language ModelingLanguage ModellingMasked Language ModelingScheduling