cs.IRcs.AIEmpirical
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Jun 18, 2026
This paper proposes G2Rec, a scalable framework for industrial-scale generative recommendation that unifies graph-based user co-engagement modeling and semantic tokenization.
Proposes a scalable framework that unifies graph-based user co-engagement modeling and semantic tokenization for industrial-scale generative recommendation
Keywords
Before reading this…
Applications
To understand this paper, make sure you know these concepts first:
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical behaviors. At the core of generative recommendation lies item tokenization, which bridges item semantics and recommendation models. However, existing methods often struggle to effectively organize and inject complex user-behavioral and item-semantic contexts into recommendation models simultaneously. On the one hand, existing graph-based integration methods, such as graph serialization and graph neural networks, either suffer from scalability issues or exploit only local graph information. On the other hand, existing semantic tokenization methods typically rely on heuristics and lack explicit supervision signals, which may lead to inaccurate or suboptimal semantic representations. To address these limitations in user interest context modeling, we propose G2Rec, a scalable framework that unifies holistic graph-based user co-engagement modeling with semantic tokenization for industrial-scale generative recommendation. Overall, G2Rec enables recommendation models to capture holistic and semantically grounded user interest prototypes without requiring ground-truth user interests, thereby providing more comprehensive and accurate modeling of user behavior contexts in industrial sequential recommendation. Online deployment across product surfaces and extensive experiments on public datasets demonstrate the superiority of G2Rec over existing methods.
ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation
This paper proposes ChronoID, a framework for time-aware semantic ID learning in…
An LLM-Powered Semantic Alignment Framework for Journal Recommendation
This paper proposes a semantic alignment framework for journal recommendation us…
Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filter…
This paper proposes Mem-GF, a memory-efficient graph filtering-based collaborati…
Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Mod…
The paper introduces Hidden Ads, a novel backdoor attack for Vision-Language Mod…
Mood-Aware Music Recommendation: Integrating User Affective Signals into Ranking Systems
This paper proposes a mood-conditioned ranking framework for music recommendatio…
Fairness Attacks on Recommender Systems
A novel structure-aware reinforcement learning-based method is proposed to exace…
EPDQ: Efficient and Privacy-Preserving Exact Distance Query on Encrypted Graphs
The paper proposes EPDQ, a tensor-based scheme that efficiently and privately co…
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
This paper proposes ShopX, a model-centric framework for intent-driven shopping…