Knowledge graph reasoning in the fully-inductive setting—where both entities and relations at test time are unseen during training—remains an open challenge. In this work, we introduce GraphOracle, a novel framework that achieves robust fully-inductive reasoning by transforming each knowledge graph into a Relation-Dependency Graph (RDG). The RDG encodes directed precedence links between relations, capturing essential compositional patterns while drastically reducing graph density. Conditioned on a query relation, a multi-head attention mechanism propagates information over the RDG to produce context-aware relation embeddings. These embeddings then guide a second GNN to perform inductive message passing over the original knowledge graph, enabling prediction on entirely new entities and relations. Comprehensive experiments on 60 benchmarks demonstrate that GraphOracle outperforms prior methods by up to 25% in fully-inductive and 28% in cross-domain scenarios. Our analysis further confirms that the compact RDG structure and attention-based propagation are key to efficient and accurate generalization

Multi-behavior Session Based Recommendations (MBSBRs) have achieved remarkable results due to considering behavioral heterogeneity in sessions. Yet most existing works only consider binary or continuous behavior dependencies and aim to predict the next item under the target behavior, neglecting users' inherent behavior habits, resulting in learning inaccurate intentions. To tackle the above issues, we propose a novelBehaviorHabits Enhanced Intention Learning framework forSessionBasedRecommendation (BHSBR). Specifically, we focus on the next item recommendation and design a global item transition graph to learn the behavior-aware semantic relationships between items, in order to mine the underlying similarity between items beyond the session. In addition, we construct a hypergraph to extract the diverse behavior habits of users and break through the limitations of temporal relationships in the session. Compared to the existing works, our behavior habit learning method learns behavior dependencies at the user level, which could capture the user's more accurate long-term intentions and reduce the impact of noise behaviors. Extensive experiments on three datasets demonstrate that the performance of our proposedBHSBRis superior to SOTA. Further ablation experiments fully illustrate the effectiveness of our various modules.

In recent years, social recommendation systems have emerged as a pivotal technology for enhancing recommendation accuracy by leveraging user social homophily and influence. Although many works have been devoted to this area, existing works still struggle to extract the beneficial structural information from social relationships that is beneficial for recommendations and neglect the inherent popularity bias in the social networks, which leads to suboptimal recommendation performances. To address these challenges, we propose a novel framework termed Causal Disentanglement-Enhanced Diffusion Denoising for Social Recommendation (CaDDiSR). This framework first employs causal graphs to disentangle the complexities of social relationships, generating user representations with high-order structures, which are subsequently used as inputs to a diffusion process to effectively denoise social networks and retain social signals beneficial for recommendation tasks. Furthermore, the framework integrates a bidirectional knowledge distillation mechanism, which balances user representations between social and recommendation contexts, thereby facilitating the effective fusion of their respective advantages while simultaneously mitigating noise interference and enhancing overall system performance. Finally, cross-domain contrastive learning is utilized to optimize user and item representations, ensuring consistency in recommendation performance across diverse scenarios. Experimental results on multiple real-world datasets demonstrate that CaDDiSR significantly outperforms existing baseline models, substantiating its superior performance.

Knowledge Graph (KG) reasoning, which aims to infer new facts from structured knowledge repositories, plays a vital role in Natural Language Processing (NLP) systems.Its effectiveness critically depends on constructing informative and contextually relevant reasoning paths.However, existing graph neural networks (GNNs) often adopt rigid, query-agnostic pathexploration strategies, limiting their ability to adapt to diverse linguistic contexts and semantic nuances.To address these limitations, we propose MoKGR, a mixture-of-experts framework that personalizes path exploration through two complementary components: (1) a mixture of length experts that adaptively selects and weights candidate path lengths according to query complexity, providing query-specific reasoning depth; and (2) a mixture of pruning experts that evaluates candidate paths from a complementary perspective, retaining the most informative paths for each query.Through comprehensive experiments on diverse benchmark, MoKGR demonstrates superior performance in both transductive and inductive settings, validating the effectiveness of personalized path exploration in KGs reasoning.1

The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph data synthesis techniques primarily focus on simplistic structural operations, lacking the capacity to generate semantically rich nodes with meaningful textual attributes—a critical limitation for real-world applications. While large language models (LLMs) demonstrate exceptional text generation capabilities, their direct application to graph synthesis is impeded by context window limitations, hallucination phenomena, and structural consistency challenges. To address these issues, we introduce \textbf{GraphMaster}—the first multi-agent framework specifically designed for graph data synthesis in data-limited environments. GraphMaster orchestrates four specialized LLM agents (Manager, Perception, Enhancement, and Evaluation) that collaboratively optimize the synthesis process through iterative refinement, ensuring both semantic coherence and structural integrity. To rigorously evaluate our approach, we create new data-limited “Sub” variants of six standard graph benchmarks, specifically designed to test synthesis capabilities under realistic constraints. Additionally, we develop a novel interpretability assessment framework that combines human evaluation with a principled Grassmannian manifold-based analysis, providing both qualitative and quantitative measures of semantic coherence. Experimental results demonstrate that GraphMaster significantly outperforms traditional synthesis methods across multiple datasets, establishing a strong foundation for advancing GFMs in data-scarce environments.

Social recommendation (SocialRS), which utilizes user social information to improve recommendation performance, has received increasing attention. Graph neural networks (GNNs) facilitate the integration of both user preference and social features in SocialRS. However, existing techniques face two challenges: 1) the inherent sparse supervision signals and noise issues in real-world social networks; 2) current social recommendation methods suffer from the neglect of user preference and social attribute heterogeneity, which hinders the extraction of preference-related information from social networks. Taking inspiration from social enhancement and contrastive learning methods, we propose a social recommendation model DSVC based on dual social view contrastive learning. Specifically, in response to the first challenge, our model derives the consistency factors of users in different augmented social views, which are used to highlight noise-resistant users and jettison preference-independent social relationships in social views. To address the second challenge, we adopt probability vectors generated from consistency factors. These vectors guide the cross-view augmentation process of the interaction graph, which helps supplement social self-supervised signals and effectively avoid noise retained due to indiscriminate augmentation. The baseline model comparison experiment, ablation experiment, parameter adjustment experiment and robustness experiment conducted on three different real-world datasets consistently validated the effectiveness of our model in improving recommendation performance.