paper-with-me

Papers

A Mutual Information Maximization Perspective of Language Representation Learning

2019-10-18 · ICLR 2020 1 · Lingpeng Kong, Cyprien de Masson d'Autume, Wang Ling, Lei Yu, Zihang Dai, Dani Yogatama

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an alternative perspective that unifies classical word embedding models (e.g., Skip-gram) and modern contextual embeddings (e.g., BERT, XLNet). In addition to enhancing our theoretical understanding of these methods, our derivation leads to a principled framework that can be used to construct new self-supervised tasks. We provide an example by drawing inspirations from related methods based on mutual information maximization that have been successful in computer vision, and introduce a simple self-supervised objective that maximizes the mutual information between a global sentence representation and n-grams in the sentence. Our analysis offers a holistic view of representation learning methods to transfer knowledge and translate progress across multiple domains (e.g., natural language processing, computer vision, audio processing).

📄 PDF Abstract BibTeX arXiv:1910.08350

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

2021-06-14 · NeurIPS 2021 12 · Kate Rakelly, Abhishek Gupta, Carlos Florensa, Sergey Levine

Mutual information maximization provides an appealing formalism for learning representations of data. In the context of reinforcement learning (RL), such representations can accelerate learning by discarding irrelevant a…

Reinforcement Learning (RL)Representation Learning

A Mutual Information Perspective on Federated Contrastive Learning

2024-05-03 · Christos Louizos, Matthias Reisser, Denis Korzhenkov

We investigate contrastive learning in the federated setting through the lens of SimCLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and…

Contrastive LearningFederated Unsupervised LearningRepresentation Learning

Evolution Is All You Need: Phylogenetic Augmentation for Contrastive Learning

2020-12-25 · Amy X. Lu, Alex X. Lu, Alan Moses

Self-supervised representation learning of biological sequence embeddings alleviates computational resource constraints on downstream tasks while circumventing expensive experimental label acquisition. However, existing …

AllContrastive LearningRepresentation Learning

Multimodal Representations Learning Based on Mutual Information Maximization and Minimization and Identity Embedding for Multimodal Sentiment Analysis

2022-01-10 · Jiahao Zheng, Sen Zhang, XiaoPing Wang, Zhigang Zeng

Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression. Although there have been many succe…

Multimodal Sentiment AnalysisSentiment Analysis

Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization

2020-10-30 · Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong 외

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross…

Contrastive LearningGeneral ClassificationRepresentation LearningSentiment Analysis+1