Graph Neural Networks on Discriminative Graphs of Words - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Graph Neural Networks on Discriminative Graphs of Words

Résumé

In light of the recent success of Graph Neural Networks (GNNs) and their ability to perform inference on complex data structures, many studies apply GNNs to the task of text classification. In most previous methods, a heterogeneous graph, containing both word and document nodes, is constructed using the entire corpus and a GNN is used to classify document nodes. In this work, we explore a new Discriminative Graph of Words Graph Neural Network (DGoW-GNN) approach encapsulating both a novel discriminative graph construction and model to classify text. In our graph construction, containing only word nodes and no document nodes, we split the training corpus into disconnected subgraphs according to their labels and weight edges by the pointwise mutual information of the represented words. Our graph construction, for which we provide theoretical motivation, allows us to reformulate the task of text classification as the task of walk classification. We also propose a new model for the graph-based classification of text, which combines a GNN and a sequence model. We evaluate our approach on seven benchmark datasets and find that it is outperformed by several state-ofthe-art baseline models. We analyse reasons for this performance difference and hypothesise under which conditions it is likely to change. Our code is publicly available at: https://github.com/abbahaddou/DGOW.
Fichier principal
Vignette du fichier
31_graph_neural_networks_on_discr.pdf (375.92 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04447653 , version 1 (08-02-2024)

Identifiants

  • HAL Id : hal-04447653 , version 1

Citer

Yassine Abbahaddou, Johannes Lutzeyer, Michalis Vazirgiannis. Graph Neural Networks on Discriminative Graphs of Words. NeurIPS New Frontiers in Graph Learning Workshop, Dec 2023, New Orleans, United States. ⟨hal-04447653⟩
11 Consultations
16 Téléchargements

Partager

Gmail Facebook X LinkedIn More