HyperAgent4POI: Dynamic Semantic Message Passing on Multi-Agent Hypergraphs for Missing-Modality Recommendation
2026-08-03 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors address the problem of missing text and images in location recommendations, which usually makes it harder to suggest places accurately. They created HyperAgent4POI, a system that fills in missing information using a method called Dynamic Semantic Message Passing within a hypergraph, helping to better understand user and place connections. Their approach uses special agents based on a language model to improve data quality and speeds up recommendations without needing repeated complex computations. Tests on real datasets show their method boosts recommendation accuracy, especially when a lot of information is missing.
Point-of-Interest (POI)Modality completionHypergraphDynamic Semantic Message Passing (DSMP)Llama language modelSemantic motifsNext POI recommendationNode representationRanking metrics (NDCG)
Authors
Jinze Wang, Yuze Liu, Tiehua Zhang, Jiong Jin, Zhu Sun
Abstract
Next Point-of-Interest (POI) recommendation benefits from textual and visual content that describes venue semantics, yet such content is often incomplete in real-world services. Missing modalities weaken POI representations and reduce the semantic evidence available for ranking. The resulting representations also provide unreliable evidence for modeling higher-order user--POI interactions. We propose HyperAgent4POI, which uses Dynamic Semantic Message Passing (DSMP) to perform modality completion and soft incidence refinement within each hypergraph layer. Persistent node agents share a frozen Llama backbone and use role-specific adapters to produce node-to-hyperedge messages. Semantic hyperedge motifs formed from these messages guide soft incidence scoring and modality completion. Final node representations are cached for online ranking without LLM calls. Experiments on three real-world LBSN datasets show consistent ranking gains over 15 baselines across modality-missing rates, while cached inference provides practical online efficiency. Under a 60% modality-missing rate, HyperAgent4POI improves NDCG@20 over the strongest baseline by 8.2% on average across the three datasets.