Deep Extreme Multi-label Learning (2017-04-12T00:00:00.000000Z)

TL;DR

This paper proposes a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously.

Abstract

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves 2L possible label sets especially when the label dimension L is huge, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by originally establishing an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems including multi-label classification, however it has not been properly introduced to XML, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Extensive experiments on public datasets for XML show that our method performs competitive against state-of-the-art result.

Authors

Junchi Yan

17 papers

Wenjie Zhang

1 papers

Liwei Wang

1 papers

TL;DR

Abstract

Authors

References59 items

Convolutional Sequence to Sequence Learning

Learning Two-Branch Neural Networks for Image-Text Matching Tasks

DiSMEC: Distributed Sparse Machines for Extreme Multi-label Classification

Densely Connected Convolutional Networks

Max-Margin DeepWalk: Discriminative Learning of Network Representation

Fully-Convolutional Siamese Networks for Object Tracking

Deep Residual Learning for Image Recognition

Sparse Local Embeddings for Extreme Multi-label Classification

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

Learning Deep Structure-Preserving Image-Text Embeddings

Network Representation Learning with Rich Text Information

Fast R-CNN

FaceNet: A unified embedding for face recognition and clustering

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Deep Metric Learning Using Triplet Network

Convolutional Neural Networks for Sentence Classification

FastXML: a fast, accurate and stable tree-classifier for extreme multi-label learning

DeepWalk: online learning of social representations

Personalized entity recommendation: a heterogeneous information network approach

Robust Bloom Filters for Large MultiLabel Classification Tasks

Distributed Representations of Words and Phrases and their Compositionality

Hidden factors and hidden topics: understanding rating dimensions with review text

Large-scale Multi-label Learning with Missing Labels

Efficient Multi-label Classification with Many Labels

Label Partitioning For Sublinear Ranking

Regularization of Neural Networks using DropConnect

Multi-label learning with millions of labels: recommending advertiser bid phrases for web pages

Feature-aware Label Space Dimension Reduction for Multi-label Classification

ImageNet classification with deep convolutional neural networks

Multilabel Classification with Principal Label Space Transformation

The Landmark Selection Method for Multiple Output Prediction

Efficient max-margin multi-label classification with applications to zero-shot learning

Enhancing Navigation on Wikipedia with Social Tags

MultiLabel Classification on Tree- and DAG-Structured Hierarchies

Deep Sparse Rectifier Neural Networks

Multi-Label Output Codes using Canonical Correlation Analysis

Node Classification in Social Networks

Multi-label learning by exploiting label dependency

Bayes Optimal Multilabel Classification via Probabilistic Classifier Chains

Large Scale Max-Margin Multi-Label Classification with Priors

Multi-Label Prediction via Compressed Sensing

Efficient Pairwise Multilabel Classification for Large-Scale Problems in the Legal Domain

Multi-Label Classification: An Overview

The challenge problem for automated detection of 101 semantic concepts in multimedia

Learning a similarity metric discriminatively, with application to face verification

Learning multi-label scene classification

Probability Estimates for Multi-class Classification by Pairwise Coupling

The link prediction problem for social networks

In ICML

Dropout: a simple way to prevent neural networks from overfitting

Pattern Recognition

Machine learning

In AISTATS

Detecting Trends in Social Bookmarking Systems: A del.icio.us Endeavor

Analyzing Social Bookmarking Systems : A del . icio . us Cookbook

Multilabel Text Classification for Automated Tag Suggestion

Effective and Efficient Multilabel Classification in Domains with Large Number of Labels

Alternating Minimization Algorithms: From Blahut-Arimoto to Expectation-Maximization

Neural Computation

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL

Alternate Names