Related papers: Learning Robust Representations via Multi-View Information Bottleneck

Learning Robust Representations via Multi-View Information Bottleneck

URL: http://arxiv.org/abs/2002.07017v2
Date: Tue, 18 Feb 2020 09:47:50 GMT
Title: Learning Robust Representations via Multi-View Information Bottleneck
Authors: Marco Federici, Anjan Dutta, Patrick Forr\'e, Nate Kushman, Zeynep Akata
Abstract summary: Original formulation requires labeled data to identify superfluous information. We extend this ability to the multi-view unsupervised setting, where two views of the same underlying entity are provided but the label is unknown. A theoretical analysis leads to the definition of a new multi-view model that produces state-of-the-art results on the Sketchy dataset and label-limited versions of the MIR-Flickr dataset.
Score: 41.65544605954621
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess information in the representation. The original formulation, however, requires labeled data to identify the superfluous information. In this work, we extend this ability to the multi-view unsupervised setting, where two views of the same underlying entity are provided but the label is unknown. This enables us to identify superfluous information as that not shared by both views. A theoretical analysis leads to the definition of a new multi-view model that produces state-of-the-art results on the Sketchy dataset and label-limited versions of the MIR-Flickr dataset. We also extend our theory to the single-view setting by taking advantage of standard data augmentation techniques, empirically showing better generalization capabilities when compared to common unsupervised approaches for representation learning.

Related papers

Discovering Common Information in Multi-view Data [35.37807004353416]
We introduce an innovative and mathematically rigorous definition for computing common information from multi-view data. We develop a novel supervised multi-view learning framework to capture both common and unique information.
arXiv Detail & Related papers (2024-06-21T10:47:06Z)
Learning Representations without Compositional Assumptions [79.12273403390311]
We propose a data-driven approach that learns feature set dependencies by representing feature sets as graph nodes and their relationships as learnable edges. We also introduce LEGATO, a novel hierarchical graph autoencoder that learns a smaller, latent graph to aggregate information from multiple views dynamically.
arXiv Detail & Related papers (2023-05-31T10:36:10Z)
Multi-View Clustering from the Perspective of Mutual Information [0.0]
We propose a novel model based on information theory termed Informative Multi-View Clustering (IMVC) IMVC extracts the common and view-specific information hidden in multi-view data and constructs a clustering-oriented comprehensive representation. We conduct extensive experiments on six benchmark datasets, and the experimental results indicate that the proposed IMVC outperforms other methods.
arXiv Detail & Related papers (2023-02-17T07:49:27Z)
Cross-view Graph Contrastive Representation Learning on Partially Aligned Multi-view Data [52.491074276133325]
Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. We propose a new cross-view graph contrastive learning framework, which integrates multi-view information to align data and learn latent representations. Experiments conducted on several real datasets demonstrate the effectiveness of the proposed method on the clustering and classification tasks.
arXiv Detail & Related papers (2022-11-08T09:19:32Z)
Variational Distillation for Multi-View Learning [104.17551354374821]
We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
arXiv Detail & Related papers (2022-06-20T03:09:46Z)
Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering [29.27475285925792]
We establish a new framework called Self-supervised Information Bottleneck based Multi-view Subspace Clustering (SIB-MSC) Inheriting the advantages from information bottleneck, SIB-MSC can learn a latent space for each view to capture common information among the latent representations of different views. Our method achieves superior performance over the related state-of-the-art methods.
arXiv Detail & Related papers (2022-04-26T15:49:59Z)
Learning Weakly-Supervised Contrastive Representations [104.42824068960668]
We present a two-stage weakly-supervised contrastive learning approach. The first stage is to cluster data according to its auxiliary information. The second stage is to learn similar representations within the same cluster and dissimilar representations for data from different clusters.
arXiv Detail & Related papers (2022-02-14T12:57:31Z)
InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction [19.176183245280267]
We introduce two widely-existing sources in knowledge bases, namely entity descriptions and multi-grained entity types. An end-to-end multi-view learning framework is proposed for relation extraction via Intact Space Representation Learning (InSRL)
arXiv Detail & Related papers (2020-12-17T02:49:46Z)
Self-supervised Learning from a Multi-view Perspective [121.63655399591681]
We show that self-supervised representations can extract task-relevant information and discard task-irrelevant information. Our theoretical framework paves the way to a larger space of self-supervised learning objective design.
arXiv Detail & Related papers (2020-06-10T00:21:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.