AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Memory Augmented Graph Neural Networks for Sequential Recommendation

Chen Ma, Liheng Ma, Yingxue Zhang, Jianing Sun, Xue Liu, Mark Coates

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Continuous-time dynamic graph learning · 245 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 MA-GNN instead of the strongest baselineSequential recommendation · CDsRecall@10: 0.0382 -> 0.0442Improved
Use MA-GNN instead of the strongest baselineSequential recommendation · BooksRecall@10: 0.0358 -> 0.0432Improved
Use MA-GNN instead of the strongest baselineSequential recommendation · ChildrenNDCG@10: 0.1007 -> 0.1137Improved
Use MA-GNN instead of the strongest baselineSequential recommendation · ComicsRecall@10: 0.1494 -> 0.1617Improved
Use MA-GNN instead of the strongest baselineSequential recommendation · ML20MNDCG@10: 0.1119 -> 0.1272Improved
Add short-term GNN interest modeling to MF (ablation)MA-GNN · CDs and BooksRecall@10: CDs: 0.0269 -> 0.0306; Books: 0.0310 -> 0.0324Improved
Add long-term interest with gated fusion to MF+S (ablation)MA-GNN · CDs and BooksRecall@10: CDs: 0.0306 -> 0.0401; Books: 0.0324 -> 0.0351Improved
Use gated fusion rather than concatenation (ablation)Short- and long-term interest fusion · CDs and BooksRecall@10: CDs: 0.0295 -> 0.0401; Books: 0.0296 -> 0.0351Improved
Use gated fusion rather than GRU fusion (ablation)Short- and long-term interest fusion · CDs and BooksRecall@10: CDs: 0.0268 -> 0.0401; Books: 0.0306 -> 0.0351Improved
Add item co-occurrence modeling (ablation)MA-GNN · CDs and BooksRecall@10: CDs: 0.0401 -> 0.0442; Books: 0.0351 -> 0.0432Improved

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