AI Paper Atlas

Research map / Graph learning / GNN architectures

Continual Graph Convolutional Network for Text Classification

Tiandeng Wu, Qijiong Liu, Yi Cao, Yao Huang, Xiao-Ming Wu, Jiandong Ding

AAAI 2023 · Graph learning › GNN architectures · approach: Graph structure learning · 7 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

Add contrastive loss · 20NG · accuracy: 89.7 -> 90.1 Improved

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
Use ContGCN with RoBERTa instead of RoBERTaGCNOffline text classification · 20NGaccuracy: 89.5 -> 90.1Improved
Use ContGCN with RoBERTa instead of RoBERTaGCNOffline text classification · R8 Reutersaccuracy: 98.2 -> 98.6Improved
Use ContGCN with XLNet instead of BertGCNOffline text classification · R52 Reutersaccuracy: 96.6 -> 97.0Improved
Use ContGCN with RoBERTa instead of RoBERTaGCNOffline text classification · Ohsumedaccuracy: 72.8 -> 73.4Improved
Use ContGCN with RoBERTa instead of RoBERTaGCNOffline text classification · Movie Review (MR)accuracy: 89.7 -> 91.3Improved
Add Wikipedia initialization (ablation)ContGCN-RoBERTa · 20NGaccuracy: 89.9 -> 90.1Improved
Add OMM updating (ablation)ContGCN-RoBERTa · 20NGaccuracy: 89.6 -> 90.1Improved
Add contrastive loss (ablation)ContGCN-RoBERTa · 20NGaccuracy: 89.7 -> 90.1Improved
Add Wikipedia initialization (ablation)ContGCN-XLNet · 20NGaccuracy: 89.8 -> 89.7Hurt
Add OMM updating (ablation)ContGCN-XLNet · 20NGaccuracy: 89.4 -> 89.7Improved
Add contrastive loss (ablation)ContGCN-XLNet · 20NGaccuracy: 89.5 -> 89.7Improved
Add OMM updating (ablation)ContGCN · 20NG online sessions 1/6–6/6accuracy: 86.0, 86.2, 86.4, 86.6, 86.9, 87.1 -> 86.3, 87.1, 87.8, 88.2, 88.7, 89.1Improved

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