AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification

Abstract

Extreme multi-label text classification (XMTC) is an important problem in the era of big data, for tagging a given text with the most relevant multiple labels from an extremely large-scale label set. XMTC can be found in many applications, such as item categorization, web page tagging, and news annotation. Traditionally most methods used bag-of-words (BOW) as inputs, ignoring word context as well as deep semantic information. Recent attempts to overcome the problems of BOW by deep learning still suffer from 1) failing to capture the important subtext for each label and 2) lack of scalability against the huge number of labels. We propose a new label tree-based deep learning model for XMTC, called AttentionXML, with two unique features: 1) a multi-label attention mechanism with raw text as input, which allows to capture the most relevant part of text to each label; and 2) a shallow and wide probabilistic label tree (PLT), which allows to handle millions of labels, especially for "tail labels". We empirically compared the performance of AttentionXML with those of eight state-of-the-art methods over six benchmark datasets, including Amazon-3M with around 3 million labels. AttentionXML outperformed all competing methods under all experimental settings. Experimental results also show that AttentionXML achieved the best performance against tail labels among label tree-based methods. The code and datasets are available at http://github.com/yourh/AttentionXML .

arXiv commentAccepted by NeurIPS 2019

Cited by in corpus (29)

• The Emerging Trends of Multi-Label Learning
• Transformers in Healthcare: A Survey
• A Survey on Text Classification: From Shallow to Deep Learning
• Overview of BioASQ 2021: The ninth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
• Overview of BioASQ 2020: The eighth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
• On Data Augmentation for Extreme Multi-label Classification
• Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
• Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification
• Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach
• LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification
• Taming Pretrained Transformers for Extreme Multi-label Text Classification
• Probabilistic Label Trees for Extreme Multi-label Classification
• LdSM: Logarithm-depth Streaming Multi-label Decision Trees
• Propensity-scored Probabilistic Label Trees
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
• HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization
• Label Disentanglement in Partition-based Extreme Multilabel Classification
• Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning
• Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy
• Unbiased Loss Functions for Extreme Classification With Missing Labels
• Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations
• Online probabilistic label trees
• Stratified Sampling for Extreme Multi-Label Data
• Learning with Holographic Reduced Representations
• Multi-granular Legal Topic Classification on Greek Legislation
• Extreme Multi-label Learning for Semantic Matching in Product Search
• On Riemannian Approach for Constrained Optimization Model in Extreme Classification Problems
• MATCH: Metadata-Aware Text Classification in A Large Hierarchy
• On-the-fly Global Embeddings Using Random Projections for Extreme Multi-label Classification