AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Interest-Shift-Aware Logical Reasoning for Efficient Long-Sequence Recommendation

Fei Li, Qingyun Gao, Enneng Yang, Jianzhe Zhao, Guibing Guo

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 0 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 ILR contrastive loss (multi-interest reasoning) to SIE + LIC-S (ablation)ELECTOR · MoTV (seq len 100)N@10: 0.400 -> 0.816Improved
add ILR contrastive loss to recent-sequence reasoning (ablation)ELECTOR variants · Amazon(500)N@10: 0.235 -> 0.454Improved
add subsequence interest extraction (SIE) to NCR (ablation)NCR · ML-1M (seq len 100)N@10: 0.207 -> 0.812Improved
add LIC-S subsequence interest correlations without ILR loss (ablation)ELECTOR base · ML-1M (seq len 100)N@10: 0.812 -> 0.693Hurt
add LIC-S subsequence interest correlations without ILR loss (ablation)ELECTOR base · Amazon(1000)N@10: 0.408 -> 0.585Improved
add recent-item interest correlation (LIC-RI) to Variant 2 (ablation)ELECTOR · Amazon(500)N@10: 0.753 -> 0.854Improved
add LIC-RI recent-interest reasoning alone (no SIE, no ILR) vs NCR (ablation)NCR · ML-1M (seq len 100)N@10: 0.207 -> 0.204No clear effect
reason over limited interest embeddings rather than all itemsNCR · Amazon(1000)training time per epoch (s): 818s -> 241s (LRM), 153s (KFM)Improved
use kernel feature maps (KFM) instead of low-rank matrix approximation (LRM) in SIEELECTOR · Amazon(1000)training time per epoch (s): 241s -> 153sImproved
ELECTOR over strongest baseline on long sequencesELECTOR · Amazon(1000)N@5: 288.02% over strongest baselineImproved
increase sequence length from 50 to 100 for NLR/NCRNCR · ML-1MN@10: 0.316 -> 0.207Hurt
increase subsequence length t (ablation)ELECTOR · sensitivity analysisaccuracy / training timeImproved

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