AI Paper Atlas

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

Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation

Peng He, Yanglei Gan, Tingting Dai, Run Lin, Xuexin Li, Yao Liu, Qiao Liu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 7 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 Global Spectral Aggregator (inter-session path) (ablation)FreqRec · BeautyHR@20: 0.1202 -> 0.1359Improved
add Local Spectral Refiner (intra-session path) (ablation)FreqRec · BeautyHR@20: 0.1215 -> 0.1359Improved
add both GSA and LSR frequency modules on top of self-attention (ablation)FreqRec · Toys & GamesHR@20: 0.0956 -> 0.1468Improved
add frequency-domain consistency loss LF (ablation)FreqRec · Toys & GamesHR@20: 0.1342 -> 0.1468Improved
keep cross-entropy loss alongside frequency loss (ablation)FreqRec · BeautyHR@20: 0.1081 -> 0.1359Improved
add the self-attention branch to FreqNet (ablation)FreqRec · BeautyHR@20: 0.1279 -> 0.1359Improved
use parallel instead of serial fusion of inter and intra paths (ablation)FreqRec · BeautyHR@10: 0.0962 -> 0.0989Improved
use parallel instead of serial fusion (ablation)FreqRec · Toys & GamesNDCG@10: 0.0655 -> 0.0653No clear effect
add the frequency-domain loss LF to SASRecSASRec · BeautyHR@10: 0.0531 -> 0.0592Improved
add the frequency-domain loss LF to BSARecBSARec · BeautyHR@10: 0.0871 -> 0.0972Improved
add the frequency-domain loss LF to DuoRecDuoRec · Toys & GamesHR@10: 0.1027 -> 0.1030No clear effect
remove GSA from FreqRec under noisy cross-domain training (ablation)FreqRec · Automotive (noisy)HR@10: 0.0495 -> 0.0521Improved

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