AI Paper Atlas

Research map / Time series / Long-term forecasting

Dynamic Multi-Context Attention Networks for Citation Forecasting of Scientific Publications

Taoran Ji, Nathan Self, Kaiqun Fu, Zhiqian Chen, Naren Ramakrishnan, Chang-Tien Lu

AAAI 2021 · Time series › Long-term forecasting · approach: Attention for time series forecasting · 3 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
Use DMA-Nets instead of PC-RNN for citation-time forecastingcitation forecasting · USPTO, 30% observationsMAE: 132.2665 -> 131.0907Improved
Use DMA-Nets instead of DotSeq2Seq for citation-time forecastingcitation forecasting · MAG, 30% observationsMAE: 47.0133 -> 42.2267Improved
Use DMA-Nets instead of PC-RNN for category predictioncitation forecasting · USPTO, 80% observationsACC: 0.8121 -> 0.8570Improved
Use DMA-Nets instead of CYAN-RNN for category predictioncitation forecasting · USPTO, 30% observationsACC: 0.8431 -> 0.8444Improved
Use DMA-Nets instead of PC-RNN for category predictioncitation forecasting · MAG, 80% observationsACC: 0.6720 -> 0.6647Hurt
Use DMA-Nets instead of CYAN-RNN for category predictioncitation forecasting · MAG, 30% observationsACC: 0.6390 -> 0.6425Improved
Add the GMTA layer (ablation)DMA-Nets · USPTO, 80% observationsMAE: 58.8086 -> 56.8676Improved
Add the GMTA layer (ablation)DMA-Nets · MAG, 80% observationsMAE: 17.4309 -> 17.2212Improved
Add the LTA layer (ablation)DMA-Nets · USPTO, 80% observationsMAE: 57.9564 -> 56.8676Improved
Add the LTA layer (ablation)DMA-Nets · MAG, 80% observationsMAE: 17.5243 -> 17.2212Improved
Reduce hidden dimension dh from the base setting (ablation)DMA-Nets · USPTO, 80% observationsMAE: 56.8676 -> 58.3457Hurt
Reduce hidden dimension dh from the base setting (ablation)DMA-Nets · USPTO, 80% observationsACC: 0.8570 -> 0.8516Hurt

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