Guandong Xu

Multi-behavior recommendation leverages diverse user interactions to capture personalized user preferences. To alleviate the data sparsity of the crucial target behavior, multi-behavior contrastive learning (MBCL) improves performance by enriching self-supervised signals from auxiliary behaviors. However, existing methods rely on heuristic augmentation techniques to construct contrastive views, which disrupt essential multi-behavior collaborative information; simultaneously, auxiliary behaviors, influenced by multiple confounders, easily introduce semantic confusion into the MBCL alignment process. Inspired by recent advances of diffusion models, we propose DiffMB, a novel diffusion contrastive learning framework. DiffMB first employs a Multi-Behavior Weight-Enhanced Graph Neural Network to capture behavioral heterogeneity through parallel encoding. At the core of DiffMB is a Hybrid Contrastive Learning (HCL) strategy that tackles this dilemma via two synergistic components. First, Target-Behavior Diffusion Contrastive Learning leverages a diffusion process to generate high-quality, semantically consistent views for the target behavior, thereby consolidating its semantics while avoiding the disruption of collaborative information. Second, Multi-Behavior Collaborative Contrastive Learning extracts valuable collaborative signals from auxiliary behaviors. Furthermore, a Dynamic Optimization Strategy is introduced to reconcile gradient conflicts in multi-task training. Extensive experiments on three datasets demonstrate that DiffMB significantly outperforms state-of-the-art baselines.

An unfair recommender system can exacerbate social biases, degrade user experience, and even pose legal and ethical risks. Therefore, detecting disadvantaged subgroups of users who exhibit significant underperformance is important for optimizing and improving recommender systems. Existing methods only identify Attribute-based Disadvantaged Subgroups ( ADS s), neglecting disadvantaged subgroups caused by the interaction process between users and items (Interaction correlated Disadvantaged Subgroups, IDS s). To address this limitation, we propose FINDUS , a fairness-oriented interaction aware disadvantaged subgroup detection approach for recommender systems. This is the first work capable of detecting IDS s. In FINDUS , a collaborative grouping mechanism is used to detect IDS s. It is based on multi round bidirectional mapping between users and items to generate interaction attributes. To overcome the attribute explosion problem caused by combinations of attribute constraints during subgroup detection, we also devise a scoring and pruning method founded on upper-bound estimation. Extensive experiments are carried out on multiple real world datasets, and the results demonstrate that FINDUS can effectively and efficiently identify a diverse set of unfairly treated user subgroups, including both ADS s and IDS s.

1. The widespread emergence of large language models (LLMs), such as OpenAI’s ChatGPT, Google’s Gemini, and DeepSeek, has transformed the way people interact with artificial intelligence (AI). Unli...

Graph-based recommender systems (GBRs) have achieved remarkable success by leveraging Graph Neural Networks (GNNs) to model complex user-item interactions and structural relationships. However, they still face major challenges in real-world environments, including out-of-distribution (OOD) generalization, dynamic user preferences, fairness, and interpretability. These limitations largely arise because conventional GNN-based recommenders rely on correlation-driven learning over observational interaction graphs, often capturing unstable or spurious associations rather than underlying causal mechanisms. Fortunately, causal learning provides a principled framework for modeling the data-generating process and identifying stable causal relationships across environments. By incorporating causal graphs, Structural Causal Models (SCMs), interventions, causal effect estimation, and counterfactual reasoning, it enables the development of more robust, adaptive, fair, and interpretable GBRs. This survey reviews causal learning in GBRs by summarizing key challenges, establishing connections between causal inference and graph neural networks, and presenting a challenge-oriented taxonomy of representative causal techniques. We further review evaluation metrics, benchmark datasets, graph construction protocols, and open-source libraries, and discuss current limitations and future research directions. Overall, this survey provides a systematic overview of causal learning in GBRs and aims to support the development of more robust and trustworthy GBRs.

The increasing integration of Artificial Intelligence (AI) into K-12 education represents a profound epistemological and pedagogical disruption. Drawing upon the discourse from the inaugural Lushan Summit organized by AI, Brain and Child Research Centre of Education University of Hong Kong, this editorial critically examines the trajectory of AI-driven educational restructuring. It explores the transition from industrial-era standardized schooling to hyper-personalized learning environments; the irreplaceability and required changes of the human educator’s role; the ethical imperatives surrounding algorithmic opacity; and the shift from static curricula to dynamic knowledge systems. By synthesizing multidisciplinary perspectives, we argue that the AI era demands not a capitulation to technological determinism, but a reimagining of education that fiercely protects and enables human agency, advanced socio-emotional skills, and metacognition.

Intelligent financial service platforms are increasingly required to deliver continuous, reliable, and interpretable stock prediction services under volatile market conditions. In such service scenarios, stock prediction is not merely a standalone forecasting task, but a reliability-sensitive service process that must integrate heterogeneous market evidence, arbitrate conflicting signals, and adapt its prediction logic as market regimes evolve. To address these issues, this paper proposes TextGrad-Trader, a graph-enhanced multimodal reasoning framework for adaptive stock prediction services. TextGrad-Trader first decomposes technical indicators, corporate fundamentals, news semantics, and relational momentum into role-specific evidence through a graph-inductive expert pool, preserving the traceability of heterogeneous signals before fusion. It then introduces Bayesian contextual gating to estimate signal credibility by jointly considering historical scenario priors and current reasoning coherence, thereby enabling reliability-aware signal arbitration. Based on the conflict-resolved evidence, an adversarial Pareto-reasoning tree evaluates candidate prediction responses under joint utility and downside-risk constraints, improving the robustness of service delivery in uncertain market states. Finally, textual gradient descent converts historical prediction feedback into reusable reasoning guidance, allowing the prompt-parameterized service policy to evolve with non-stationary markets. Experiments on real-world stock data show that TextGrad-Trader improves risk-aware prediction performance, and ablation analyses verify the contribution of its major service components. The source code is publicly available on GitHub.