paper-with-me

홈 › Papers

Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax

2024-10-09 · Ivan Butakov, Alexander Semenenko, Alexander Tolmachev, Andrey Gladkov, Marina Munkhoeva, Alexey Frolov

Deep InfoMax (DIM) is a well-established method for self-supervised representation learning (SSRL) based on maximization of the mutual information between the input and the output of a deep neural network encoder. Despite the DIM and contrastive SSRL in general being well-explored, the task of learning representations conforming to a specific distribution (i.e., distribution matching, DM) is still under-addressed. Motivated by the importance of DM to several downstream tasks (including generative modeling, disentanglement, outliers detection and other), we enhance DIM to enable automatic matching of learned representations to a selected prior distribution. To achieve this, we propose injecting an independent noise into the normalized outputs of the encoder, while keeping the same InfoMax training objective. We show that such modification allows for learning uniformly and normally distributed representations, as well as representations of other absolutely continuous distributions. Our approach is tested on various downstream tasks. The results indicate a moderate trade-off between the performance on the downstream tasks and quality of DM.

📄 PDF Abstract BibTeX arXiv:2410.06993

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementRepresentation Learning

Similar Papers 제목 키워드 기반

Smooth InfoMax -- Towards easier Post-Hoc interpretability

2024-08-23 · Fabian Denoodt, Bart de Boer, José Oramas

We introduce Smooth InfoMax (SIM), a novel method for self-supervised representation learning that incorporates an interpretability constraint into the learned representations at various depths of the neural network. SIM…

DecoderRepresentation Learning

HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization

2021-04-12 · NAACL 2021 4 · Zhongfen Deng, Hao Peng, Dongxiao He, JianXin Li 외

The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. First, it correlates each text sample with all labels in the dataset which contains irrelevant information. Second, it do…

General ClassificationRepresentation Learningtext-classificationText Classification

Flow Matching with Injected Noise for Offline-to-Online Reinforcement Learning

2026-02-20 · Yongjae Shin, Jongseong Chae, Jongeui Park, Youngchul Sung arxiv

Generative models have recently demonstrated remarkable success across diverse domains, motivating their adoption as expressive policies in reinforcement learning (RL). While they have shown strong performance in offline…

Reinforcement LearningOffline RL

Learning deep representations by mutual information estimation and maximization

2018-08-20 · ICLR 2019 5 · R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal 외

In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporat…

General ClassificationMutual Information EstimationRepresentation Learning

Graph Embedding Using Infomax for ASD Classification and Brain Functional Difference Detection

2019-08-09 · Xiaoxiao Li, Nicha C. Dvornek, Juntang Zhuang, Pamela Ventola 외

Significant progress has been made using fMRI to characterize the brain changes that occur in ASD, a complex neuro-developmental disorder. However, due to the high dimensionality and low signal-to-noise ratio of fMRI, em…

ClassificationGeneral ClassificationGraph EmbeddingGraph Neural Network