AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Label Patent Categorization with Non-Local Attention-Based Graph Convolutional Network

Pingjie Tang, Meng Jiang, Bryan (Ning) Xia, Jed W. Pitera, Jeffrey Welser, Nitesh V. Chawla

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 46 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
replace GraphSAGE with attention-based BiLSTM aggregator (A-GCN) (ablation)GraphSAGE · Patent CIRCA 45kP@1: 72.95 -> 75.74Improved
add AttentionXML-style label attention to A-GCN (ablation)A-GCN · Patent CIRCA 45kP@1: 75.74 -> 76.72Improved
replace label attention with adaptive non-local second-order attention (ablation)A-GCN+LA · Patent CIRCA 45kP@1: 76.72 -> 78.30Improved
replace label attention with adaptive non-local second-order attention (ablation)A-GCN+LA · Patent CIRCA 45knDCG@5: 77.20 -> 78.28Improved
add adaptive non-local second-order attention to A-GCN (ablation)A-GCN · Patent CIRCA 45kP@5: 34.92 -> 36.41Improved
add phrase features to bag-of-words (ablation)Parabel · Patent CIRCA 45kP@1: 75.10 -> 75.79Improved
add phrase features to bag-of-words (ablation)FastXML · Patent CIRCA 45kP@1: 73.10 -> 73.92Improved
use 20 attention heads (ablation)A-GCN+A-NLSOA · Patent CIRCA 45kP@1Improved
use sliding window size 20 for PMI instead of 5, 10 or 25 (ablation)A-GCN+A-NLSOA · Patent CIRCA 45kP@1Improved
use covariance without power normalization (ablation)A-NLSOA · Patent CIRCA 45kP@1Improved
use softmax rather than sigmoid output (ablation)A-GCN+A-NLSOA · Patent CIRCA 45kP@1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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