LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification
Multi-label text classification (MLTC) is an attractive and challenging task in natural language processing (NLP). Compared with single-label text classification, MLTC has a wider range of applications in practice. In this paper, we propose a label-interpretable graph convolutional network model to solve the MLTC problem by modeling tokens and labels as nodes in a heterogeneous graph. In this way, we are able to take into account multiple relationships including token-level relationships. Besides, the model allows better interpretability for predicted labels as the token-label edges are exposed. We evaluate our method on four real-world datasets and it achieves competitive scores against selected baseline methods. Specifically, this model achieves a gain of 0.14 on the F1 score in the small label set MLTC, and 0.07 in the large label set scenario.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationMulti Label Text ClassificationMulti-Label Text Classificationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Directed Graph Auto-Encoders
We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representa…
DecoderLink PredictionGKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition
Multi-Label Image Recognition (MLIR) is a challenging task that aims to predict multiple object labels in a single image while modeling the complex relationships between labels and image regions. Although convolutional n…
graph constructionMulti-Label ClassificationMulti-Label Image RecognitionAttention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurre…
Multi-Label ClassificationMulti-Label Image RecognitionMulti-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels
Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algor…
Graph EmbeddingGraph LearningSelf-Supervised LearningSpectral Pyramid Graph Attention Network for Hyperspectral Image Classification
Convolutional neural networks (CNN) have made significant advances in hyperspectral image (HSI) classification. However, standard convolutional kernel neglects the intrinsic connections between data points, resulting in …
ClassificationGeneral ClassificationGraph AttentionHyperspectral Image Classification+2