RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation

2026-09-30

AI Summary

Existing sequential recommendation models typically process all interaction data uniformly, overlooking behavioral differences across sessions. To address this limitation, this work proposes RouteRec, a novel framework that pioneers the use of observed session behaviors—such as interaction pace—as routing criteria to drive a Mixture-of-Experts (MoE) architecture for multi-granularity conditional computation. Specifically, the method extracts behavioral features from macro, meso, and micro perspectives to precisely guide dynamic expert routing. Extensive experiments on six benchmark datasets demonstrate that RouteRec achieves the highest average ranking and significantly outperforms existing baselines, thereby validating the effectiveness of the behavior-guided routing mechanism.

Abstract

Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all sessions through the same parameterized blocks, regardless of their behavioral differences. Mixture of Experts (MoE) enables conditional computation, but it leaves open what should guide expert allocation. We propose RouteRec, a sequential recommender that uses observed session behavior as the routing criterion. RouteRec summarizes four types of behavioral evidence from sessionized histories: interaction tempo, item-group focus, repetition and carryover, and popularity tendency. It uses these cues to route computation at macro, mid, and micro scopes. Cue-derived scores first select expert groups; within each selected group, the current backbone state then refines expert selection. Across six public datasets and 18 dataset-metric combinations, RouteRec ranks first in 12 and second in three, yielding the best overall average rank of 1.61 compared with 4.11 for the next-best baseline. Additional analyses suggest that the behavioral cues guide expert allocation beyond added capacity and produce routing patterns aligned with observed behavior. Our code is available at https://github.com/jy1559/RouteRec

Problem

• Sequential Recommendation
• Mixture of Experts
• Behavioral Patterns
• Conditional Computation
• Sparse Routing

Innovation

• Sequential Recommendation
• Mixture of Experts
• Sparse Routing
• Behavioral Cues
• Conditional Computation