AI Paper Atlas

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

Prompt-Based Multi-Interest Learning Method for Sequential Recommendation

Xue Dong, Xuemeng Song, Tongliang Liu, Weili Guan

TPAMI 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 11 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 learnable prompt embeddings to the extractor and aggregator inputs (ablation)PoMRec base · ML-1MRecall@5: 0.3068 -> 0.3129Improved
add learnable prompt embeddings (ablation)PoMRec base · BeautyRecall@5: 0.1193 -> 0.1299Improved
add learnable prompt embeddings (ablation)PoMRec base · Movies & TVRecall@5: 0.2429 -> 0.2498Improved
add dispersion (variance) embedding to centrality (ablation)PoMRec base · ML-1MRecall@5: 0.3068 -> 0.3108Improved
add dispersion (variance) embedding to centrality (ablation)PoMRec base · BeautyRecall@5: 0.1193 -> 0.1293Improved
add dispersion (variance) embedding to centrality (ablation)PoMRec base · Movies & TVRecall@5: 0.2429 -> 0.2591Improved
add both prompts and dispersion (ablation)PoMRec base · BeautyRecall@5: 0.1193 -> 0.1456Improved
add both prompts and dispersion (ablation)PoMRec base · Movies & TVRecall@5: 0.2429 -> 0.2747Improved
deploy prompts and dispersion on MINERMINER · ML-1MRecall@5: 0.2758 -> 0.2975Improved
deploy prompts and dispersion on TiMiRec (single item embedding)TiMiRec · ML-1MRecall@5: 0.3091 -> 0.3222Improved
deploy prompts and dispersion on TiMiRecTiMiRec · Movies & TVRecall@5: 0.2506 -> 0.2735Improved
vary number of user interests K from 1 to 5 (ablation)PoMRec · ML-1M / Movies & TVRecall@5: best K=2 on ML-1M, K=3 on Movies & TVMixed

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