AI Paper Atlas

Research map / Graph learning / GNN architectures

Tensor Graph Convolutional Networks for Text Classification

Xien Liu, Xinxin You, Xiao Zhang, Ji Wu, Ping Lv

AAAI 2020 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 309 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add SemGraph to the graph tensor (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8688 -> 0.8774; 0.9776 -> 0.9804; 0.9334 -> 0.9505; 0.6917 -> 0.7011; 0.7763 -> 0.7791Mixed
Add SynGraph to the graph tensor (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8707 -> 0.8774; 0.9753 -> 0.9804; 0.9529 -> 0.9505; 0.6854 -> 0.7011; 0.7710 -> 0.7791Mixed
Add SeqGraph to the graph tensor (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8699 -> 0.8774; 0.9753 -> 0.9804; 0.9486 -> 0.9505; 0.6921 -> 0.7011; 0.7746 -> 0.7791Mixed
Add inter-graph propagation after intra-graph propagation (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8701 -> 0.8774; 0.9808 -> 0.9804; 0.9498 -> 0.9505; 0.6723 -> 0.7011; 0.7656 -> 0.7791Mixed
Preserve separate graph representations and learn with TensorGCN instead of merging edges (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8721 -> 0.8774; 0.9749 -> 0.9804; 0.9463 -> 0.9505; 0.6951 -> 0.7011; 0.7532 -> 0.7791Mixed
Use only SeqGraph rather than all three graphs (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8634 -> 0.8774; 0.9707 -> 0.9804; 0.9356 -> 0.9505; 0.6836 -> 0.7011; 0.7674 -> 0.7791Hurt
Use only SynGraph rather than all three graphs (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8478 -> 0.8774; 0.9534 -> 0.9804; 0.9299 -> 0.9505; 0.6658 -> 0.7011; 0.7496 -> 0.7791Hurt
Use only SemGraph rather than all three graphs (ablation)TensorGCN · 20NG, R8, R52, Ohsumed, MRaccuracy: 0.8517 -> 0.8774; 0.9520 -> 0.9804; 0.9245 -> 0.9505; 0.6626 -> 0.7011; 0.7620 -> 0.7791Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy