Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP
This work addresses the efficiency and effectiveness of text classification methods for researchers and practitioners, showing that simpler models can match or exceed complex graph-based approaches, which is incremental but challenges current trends.
The paper tackles the problem of text classification by comparing Bag-of-Words, graph-based, and sequence-based methods, finding that a wide MLP with BoW outperforms some graph-based models and is competitive with others, while fine-tuned BERT and DistilBERT achieve state-of-the-art results, questioning the necessity of synthetic graphs in text classifiers.
Graph neural networks have triggered a resurgence of graph-based text classification methods, defining today's state of the art. We show that a wide multi-layer perceptron (MLP) using a Bag-of-Words (BoW) outperforms the recent graph-based models TextGCN and HeteGCN in an inductive text classification setting and is comparable with HyperGAT. Moreover, we fine-tune a sequence-based BERT and a lightweight DistilBERT model, which both outperform all state-of-the-art models. These results question the importance of synthetic graphs used in modern text classifiers. In terms of efficiency, DistilBERT is still twice as large as our BoW-based wide MLP, while graph-based models like TextGCN require setting up an $\mathcal{O}(N^2)$ graph, where $N$ is the vocabulary plus corpus size. Finally, since Transformers need to compute $\mathcal{O}(L^2)$ attention weights with sequence length $L$, the MLP models show higher training and inference speeds on datasets with long sequences.