Papers › MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network

MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network

24 Feb 202012th International Conference on Agents and Artificial Intelligence ICAART 2020 2archive 2025-07-28

Ankit Pal, Muru Selvakumar and Malaikannan Sankarasubbu

In Multi-Label Text Classification (MLTC), one sample can belong to more than one class. It is observed that most MLTC tasks, there are dependencies or correlations among labels. Existing methods tend to ignore the relationship among labels. In this paper, a graph attention network-based model is proposed to capture the attentive dependency structure among the labels. The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task. The generated classifiers are applied to sentence feature vectors obtained from the text feature extraction network(BiLSTM) to enable end-to-end training. Attention allows the system to assign different weights to neighbor nodes per label, thus allowing it to learn the dependencies among labels implicitly. The results of the proposed model are validated on five real-world MLTC datasets. The proposed model achieves similar or better performance compared to the previous state-of-the-art models.

Paper PDF Code

Code

akash18tripathi/MAGNET-Multi-Label-Text-Classi-cation-using-Attention-based-Graph-Neural-Network official report

adrinta/MAGNET pytorch 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

Document Classification General Classification Graph Attention Graph Neural Network Graph Representation Learning Multi Label Text Classification Multi-Label Text Classification Sentence Text Classification text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Document Classification	AAPD	MAGNET	F1	69.6	#2 of 2	Archive leaderboard	report
Document Classification	Reuters-21578	MAGNET	F1	89.9	#4 of 8	Archive leaderboard	report
Multi-Label Text Classification	AAPD	MAGNET	F1	69.6	#3 of 5	Archive leaderboard	report
Multi-Label Text Classification	RCV1-v2	MAGNET	Micro-F1	88.5	#1 of 1	Archive leaderboard	report
Multi-Label Text Classification	Reuters-21578	MAGNET	Micro-F1	89.9	#6 of 7	Archive leaderboard	report
Multi-Label Text Classification	Slashdot	MAGNET	Micro-F1	56.8	#1 of 1	Archive leaderboard	report
Text Classification	RCV1	MAGNET	Micro F1	88.5	#3 of 4	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