Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation

2025-07-06

AI Summary

Existing session-based recommendation (SBR) methods are limited to intra-session modeling, neglecting inter-session dependencies, and rely heavily on item ID co-occurrence while ignoring semantic nuances—making them vulnerable to noise. To address these limitations, we propose a hierarchical intent-guided cross-session recommendation framework. First, we construct a session graph neural network to explicitly model cross-session item transition patterns. Second, we integrate a plug-and-play, large language model–driven semantic module to enrich fine-grained item representations. Third, we design an intent-guided denoising mechanism coupled with multi-granularity contrastive learning to jointly capture users’ dynamic short-term preferences and long-term, multi-level intentions. Extensive experiments on multiple public benchmarks demonstrate significant improvements over state-of-the-art methods, validating the framework’s accuracy, robustness against noise, and generalization capability.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Semi-Supervised Learning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Session-based Recommendation (SBR) aims to predict the next item a user will likely engage with, using their interaction sequence within an anonymous session. Existing SBR models often focus only on single-session information, ignoring inter-session relationships and valuable cross-session insights. Some methods try to include inter-session data but struggle with noise and irrelevant information, reducing performance. Additionally, most models rely on item ID co-occurrence and overlook rich semantic details, limiting their ability to capture fine-grained item features. To address these challenges, we propose a novel hierarchical intent-guided optimization approach with pluggable LLM-driven semantic learning for session-based recommendations, called HIPHOP. First, we introduce a pluggable embedding module based on large language models (LLMs) to generate high-quality semantic representations, enhancing item embeddings. Second, HIPHOP utilizes graph neural networks (GNNs) to model item transition relationships and incorporates a dynamic multi-intent capturing module to address users' diverse interests within a session. Additionally, we design a hierarchical inter-session similarity learning module, guided by user intent, to capture global and local session relationships, effectively exploring users' long-term and short-term interests. To mitigate noise, an intent-guided denoising strategy is applied during inter-session learning. Finally, we enhance the model's discriminative capability by using contrastive learning to optimize session representations. Experiments on multiple datasets show that HIPHOP significantly outperforms existing methods, demonstrating its effectiveness in improving recommendation quality. Our code is available: https://github.com/hjx159/HIPHOP.

Problem

• SBR models ignore inter-session relationships and cross-session insights
• Existing methods struggle with noise and irrelevant inter-session data
• Most models overlook semantic details, limiting fine-grained item features

Innovation

• Pluggable LLM embedding for semantic item representations
• GNNs and dynamic multi-intent capturing for session modeling
• Hierarchical intent-guided inter-session similarity learning