GCTMR: Graph Contrastive Transformer for Multibehavior Recommendation

POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment

The proposed LLM-augmented Multi-Graph Contrastive Learning (LLM-MGCL) is a multi-graph neural network that uses semantic and spatial information about items to extend the LightGCN backbone with two auxiliary item-item graphs that outperforms classical collaborative filtering, matrix factorization, and interaction-only graph neural network baselines.

LRGCL: LLM-refined graph contrastive learning for review-based recommendation

Review-based recommendations commonly construct user-item interaction graphs in which textual review semantics serve as edge attributes. However, two practical limitations persist. First, raw reviews are inherently noisy: they often contain personal anecdotes, emotional expressions, and redundant phrasing that interfere with the preference-relevant signal on each edge. Second, many widely used graph contrastive learning methods generate positive views through random node or edge dropping, which may inadvertently discard semantically critical interactions and degrade the quality of learned representations. Although recent neighbor-aware methods have begun to address this limitation from structural or latent-semantic perspectives, review-based recommendation still lacks an edge-level semantic-preserving contrastive strategy that explicitly uses review evidence to protect key user-item interactions. To tackle these challenges, we propose LRGCL, an LLM-Refined Graph Contrastive Learning model for personalized recommendation. LRGCL first employs a large language model to refine each raw review into a concise, aspect-focused text that retains only key preference-feature information, and then encodes the refined review to obtain the edge semantic representation of the user-item bipartite graph. LRGCL further introduces a semantic-preserving contrastive objective in which key interaction edges are identified and preserved in augmented graph views, while only non-critical edges are dropped. Results across multiple datasets confirm that LRGCL achieves the lowest MSE and MAE among strong rating-based and review-based baselines, with especially clear MSE gains and smaller MAE margins on some domains. Ablation studies further verify the effectiveness of LLM-based review refinement and graph contrastive learning.

D3MBR: Dual-Level Diffusion Denoiser with Preference Guidance for Multi-Behavior Recommendation

Multi-Behavior Recommendation (MBR) integrates rich auxiliary behaviors to enhance user preference modeling in target behaviors, garnering wide research attention. Existing efforts focus on improving the modeling capability of MBR via sophisticated models based on fixed datasets, which are essentially model-centric. However, they overlook the potential data quality issues, such as noise. To bridge this gap, we reshape the denoising problem as a clean data generation task, and propose a noise-free generation paradigm in a data-centric perspective. Based on this paradigm, driven by the generation and denoising capabilities of the Diffusion Models, we devise a Dual-level Diffusion Denoiser with preference guidance (D \({}^{3}\) MBR). D \({}^{3}\) MBR tailors to the distinct noise characteristics of target and auxiliary behaviors. Specifically, for the target behavior, we propose a representation-level denoising strategy that utilizes collaborative preference signals to guide a diffusion denoiser in generating noise-free representations. For auxiliary behaviors, we design an interaction-level denoising strategy that uses denoised user preferences from the target behavior to direct another diffusion denoiser in generating clean interactions. To validate the effectiveness, we integrate D \({}^{3}\) MBR with advanced MBR models and achieve great performance improvements across four datasets. These results highlight the potential of our method in advancing MBR by addressing data quality issues.

Bridging the Semantic Gap: Leveraging LLMs for Hierarchical Interest Evolution in Sequential Recommendation

Rethinking Generalization in Graphs: A Hierarchical Interaction Perspective for Generalist Detection

With the increasing heterogeneity of social networks and online interaction systems, generalist graph anomaly detection (GAD) has become essential for identifying abnormal and fraudulent behaviors in complex environments. However, most existing GAD approaches rely heavily on domain-specific semantic alignment, which substantially restricts their ability to learn transferable node representations and often leads to poor generalization on unseen graph domains. To address this challenge, we propose HIerarchical Interaction MOdeling for zero-shot generalist GAD (termed HIMO-GAD). HIMO-GAD enables anomaly detection across diverse graph domains without retraining or access to target-domain supervision by modeling the evolutionary trajectories of node representations across hierarchical structural depths, thereby capturing interaction patterns that exhibit strong cross-domain stability. Specifically, HIMO-GAD integrates two core components: (1) a Dynamic Interaction Modeling Module that characterizes cross-layer interaction evolution to extract transferable representations, and (2) an Anomaly-Aware Regulation Mechanism that combines gradient immunity and centralization regularization to suppress overfitting and stabilize cross-domain generalization. Extensive experiments on multiple real-world graph datasets demonstrate that HIMO-GAD consistently outperforms state-of-the-art baselines in strict zero-shot settings, achieving up to a 10% improvement in key evaluation metrics and exhibiting strong generalization across heterogeneous graph domains.

SBFRec: Semantic-Behavioral Fusion with Trajectory Smoothing for Generative Sequential Recommendation

Generative diffusion/flow-based models have recently shown strong potential for sequential recommendation, but their performance can be brittle when conditional signals from user histories are weak and semantic augmentation or routing is unreliable. In addition, common generative objectives may be misaligned with Top-K ranking behavior, which can exacerbate popularity bias under sparse and skewed interactions. We propose SBFRec, a Semantic-Behavioral Flow Matching framework for generative sequential recommendation. SBFRec adopts a stacked dual-branch encoder that combines a bidirectional RG-LRU behavioral branch for capturing sequential transition patterns with a sparse MoE semantic adapter for injecting pretrained priors, and fuses them through a shared residual stream with delta gating. We further introduce Popularity-Aware Adaptive Fusion (PAAF), a sequence-level routing mechanism that learns adaptive branch preference conditioned on the popularity profile, enabling the model to leverage the more reliable signal source for each sequence. The encoder conditions a flow-matching decoder for generative recommendation, and is trained with a multi-task objective augmented with dual-branch regularization to prevent branch collapse and encourage complementary signals from both branches. Experiments on four benchmark datasets show that SBFRec achieves an average 6.52% improvement over state-of-the-art methods on Top-K ranking metrics.