Papers › Message Passing Attention Networks for Document Understanding

Message Passing Attention Networks for Document Understanding

17 Aug 2019arXiv:1908.06267archive 2025-07-28

Giannis Nikolentzos, Antoine J. -P. Tixier, Michalis Vazirgiannis

Graph neural networks have recently emerged as a very effective framework for processing graph-structured data. These models have achieved state-of-the-art performance in many tasks. Most graph neural networks can be described in terms of message passing, vertex update, and readout functions. In this paper, we represent documents as word co-occurrence networks and propose an application of the message passing framework to NLP, the Message Passing Attention network for Document understanding (MPAD). We also propose several hierarchical variants of MPAD. Experiments conducted on 10 standard text classification datasets show that our architectures are competitive with the state-of-the-art. Ablation studies reveal further insights about the impact of the different components on performance. Code is publicly available at: https://github.com/giannisnik/mpad .

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

giannisnik/mpad officialmentioned in papermentioned on GitHubpytorch report
Tixierae/gow_tools mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Modal Document ClassificationText Classificationdocument understandingtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Classification BBCSport MPAD-path Accuracy 99.59 #1 of 4 Archive leaderboard report
Document Classification MPQA MPAD-path Accuracy 89.81 #1 of 1 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification MPAD-path Accuracy 87.75 #70 of 87 Archive leaderboard report
Sentiment Analysis SST-5 Fine-grained classification MPAD-path Accuracy 49.68 #19 of 31 Archive leaderboard report
Text Classification TREC-6 MPAD-path Error 6.2 #12 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections