Pairwise Instance Relation Augmentation for Long-tailed Multi-label Text Classification

• URL: http://arxiv.org/abs/2211.10685v1
• Date: Sat, 19 Nov 2022 12:45:54 GMT
• Title: Pairwise Instance Relation Augmentation for Long-tailed Multi-label Text Classification
• Authors: Lin Xiao, Pengyu Xu, Liping Jing and Xiangliang Zhang
• Abstract summary: We propose a Pairwise Instance Relation Augmentation Network (PIRAN) to augment tailed-label documents for balancing tail labels and head labels. PIRAN consistently outperforms the SOTA methods, and dramatically improves the performance of tail labels.
• Score: 38.66674700075432
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-label text classification (MLTC) is one of the key tasks in natural language processing. It aims to assign multiple target labels to one document. Due to the uneven popularity of labels, the number of documents per label follows a long-tailed distribution in most cases. It is much more challenging to learn classifiers for data-scarce tail labels than for data-rich head labels. The main reason is that head labels usually have sufficient information, e.g., a large intra-class diversity, while tail labels do not. In response, we propose a Pairwise Instance Relation Augmentation Network (PIRAN) to augment tailed-label documents for balancing tail labels and head labels. PIRAN consists of a relation collector and an instance generator. The former aims to extract the document pairwise relations from head labels. Taking these relations as perturbations, the latter tries to generate new document instances in high-level feature space around the limited given tailed-label instances. Meanwhile, two regularizers (diversity and consistency) are designed to constrain the generation process. The consistency-regularizer encourages the variance of tail labels to be close to head labels and further balances the whole datasets. And diversity-regularizer makes sure the generated instances have diversity and avoids generating redundant instances. Extensive experimental results on three benchmark datasets demonstrate that PIRAN consistently outperforms the SOTA methods, and dramatically improves the performance of tail labels.

Related papers

• Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification [85.76130799062379]
  We study how false negative labels affect the model's explanation. We propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels.
  arXiv  Detail & Related papers  (2023-04-04T14:00:59Z)
• Review of Extreme Multilabel Classification [1.888738346075831]
  Extreme multilabel classification or XML, is an active area of interest in machine learning. The community has come up with a useful set of metrics to identify correctly the prediction for head or tail labels.
  arXiv  Detail & Related papers  (2023-02-12T18:29:20Z)
• Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling [39.76268402567324]
  We construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies. Label correlations are leveraged to enhance semantic-label interactions. We also propose the label-aware inter-dependent decoding mechanism to further exploit the label correlations for decoding.
  arXiv  Detail & Related papers  (2022-10-19T08:21:43Z)
• Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning [6.1538971100140145]
  We introduce a novel approach with multi-task learning to enhance label correlation feedback. We propose two auxiliary label co-occurrence prediction tasks to enhance label correlation learning.
  arXiv  Detail & Related papers  (2021-06-06T12:26:14Z)
• MATCH: Metadata-Aware Text Classification in A Large Hierarchy [60.59183151617578]
  MATCH is an end-to-end framework that leverages both metadata and hierarchy information. We propose different ways to regularize the parameters and output probability of each child label by its parents. Experiments on two massive text datasets with large-scale label hierarchies demonstrate the effectiveness of MATCH.
  arXiv  Detail & Related papers  (2021-02-15T05:23:08Z)
• Does Head Label Help for Long-Tailed Multi-Label Text Classification [45.762555329467446]
  In real applications, the distribution of label frequency often exhibits a long tail, i.e., a few labels are associated with a large number of documents. We propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to data-poor tail labels.
  arXiv  Detail & Related papers  (2021-01-24T12:31:39Z)
• A Study on the Autoregressive and non-Autoregressive Multi-label Learning [77.11075863067131]
  We propose a self-attention based variational encoder-model to extract the label-label and label-feature dependencies jointly. Our model can therefore be used to predict all labels in parallel while still including both label-label and label-feature dependencies.
  arXiv  Detail & Related papers  (2020-12-03T05:41:44Z)
• Unsupervised Person Re-identification via Multi-label Classification [55.65870468861157]
  This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels. Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction. To boost the ReID model training efficiency in multi-label classification, we propose the memory-based multi-label classification loss (MMCL)
  arXiv  Detail & Related papers  (2020-04-20T12:13:43Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.