Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification Using Graph Neural Networks?

• URL: http://arxiv.org/abs/2305.14578v2
• Date: Mon, 22 Jan 2024 14:13:51 GMT
• Title: Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification Using Graph Neural Networks?
• Authors: Margarita Bugue\~no, Gerard de Melo
• Abstract summary: This work extensively investigates graph representation methods for text classification. We compare different graph construction schemes using a variety of GNN architectures and setups. Two Transformer-based large language models are also included to complement the study.
• Score: 25.898812694174772
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the success of Graph Neural Networks (GNNs) for structure-aware machine learning, many studies have explored their use for text classification, but mostly in specific domains with limited data characteristics. Moreover, some strategies prior to GNNs relied on graph mining and classical machine learning, making it difficult to assess their effectiveness in modern settings. This work extensively investigates graph representation methods for text classification, identifying practical implications and open challenges. We compare different graph construction schemes using a variety of GNN architectures and setups across five datasets, encompassing short and long documents as well as unbalanced scenarios in diverse domains. Two Transformer-based large language models are also included to complement the study. The results show that i) although the effectiveness of graphs depends on the textual input features and domain, simple graph constructions perform better the longer the documents are, ii) graph representations are especially beneficial for longer documents, outperforming Transformer-based models, iii) graph methods are particularly efficient at solving the task.

Related papers

• Parameter-Efficient Tuning Large Language Models for Graph Representation Learning [62.26278815157628]
  We introduce Graph-aware. Efficient Fine-Tuning - GPEFT, a novel approach for efficient graph representation learning. We use a graph neural network (GNN) to encode structural information from neighboring nodes into a graph prompt. We validate our approach through comprehensive experiments conducted on 8 different text-rich graphs, observing an average improvement of 2% in hit@1 and Mean Reciprocal Rank (MRR) in link prediction evaluations.
  arXiv  Detail & Related papers  (2024-04-28T18:36:59Z)
• UniGraph: Learning a Cross-Domain Graph Foundation Model From Natural Language [41.722898353772656]
  We present our UniGraph framework, designed to train a graph foundation model capable of generalizing to unseen graphs and tasks across diverse domains. We propose a cascaded architecture of Language Models (LMs) and Graph Neural Networks (GNNs) as backbone networks with a self-supervised training objective based on Masked Graph Modeling (MGM) Our comprehensive experiments across various graph learning tasks and domains demonstrate the model's effectiveness in self-supervised representation learning on unseen graphs, few-shot in-context transfer, and zero-shot transfer.
  arXiv  Detail & Related papers  (2024-02-21T09:06:31Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications [38.83545631999851]
  We propose a framework of graph-aware language model pre-training on a large graph corpus. We conduct experiments on Amazon's real internal datasets and large public datasets.
  arXiv  Detail & Related papers  (2023-06-05T04:46:44Z)
• ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings [20.25180279903009]
  We propose Contrastive Graph-Text pretraining (ConGraT) for jointly learning separate representations of texts and nodes in a text-attributed graph (TAG) Our method trains a language model (LM) and a graph neural network (GNN) to align their representations in a common latent space using a batch-wise contrastive learning objective inspired by CLIP. Experiments demonstrate that ConGraT outperforms baselines on various downstream tasks, including node and text category classification, link prediction, and language modeling.
  arXiv  Detail & Related papers  (2023-05-23T17:53:30Z)
• State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
  Graph-level learning has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures. Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
  arXiv  Detail & Related papers  (2023-01-14T09:15:49Z)
• A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features [61.92791503017341]
  Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data. The best models for such data types in most standard supervised learning settings with IID (non-graph) data are not easily incorporated into a GNN. Here we propose a robust stacking framework that fuses graph-aware propagation with arbitrary models intended for IID data.
  arXiv  Detail & Related papers  (2022-06-16T22:46:33Z)
• GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph [53.70520466556453]
  We propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models. With the proposed architecture, the text encoding and the graph aggregation are fused into an iterative workflow. In addition, a progressive learning strategy is introduced, where the model is successively trained on manipulated data and original data to reinforce its capability of integrating information on graph.
  arXiv  Detail & Related papers  (2021-05-06T12:20:41Z)
• Co-embedding of Nodes and Edges with Graph Neural Networks [13.020745622327894]
  Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space. CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space. Our approach achieves or matches the state-of-the-art performance in four graph learning tasks.
  arXiv  Detail & Related papers  (2020-10-25T22:39:31Z)
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [62.73470368851127]
  Graph representation learning has emerged as a powerful technique for addressing real-world problems. We design Graph Contrastive Coding -- a self-supervised graph neural network pre-training framework. We conduct experiments on three graph learning tasks and ten graph datasets.
  arXiv  Detail & Related papers  (2020-06-17T16:18:35Z)
• Which way? Direction-Aware Attributed Graph Embedding [2.429993132301275]
  Graph embedding algorithms are used to efficiently represent a graph in a continuous vector space. One aspect that is often overlooked is whether the graph is directed or not. This study presents a novel text-enriched, direction-aware algorithm called DIAGRAM.
  arXiv  Detail & Related papers  (2020-01-30T13:08:19Z)

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.