User preference modeling based on hypergraphs has shown significant potential in recommender systems. However, existing methods model complex higher-order relations rely on existing hypergraph structures, such well-constructed hypergraphs are not readily accessible in every situation. Furthermore, since existing methods perform message-passing based on the same hypergraph convolution function, they often overlook diverse relation patterns, thus lacking precision. In this work, we propose an Enhanced Recommendation Framework with Hypergraph Mixture of Experts (HMoRec). Specifically, we first employ a sparse optimal transport clustering mechanism to generate high-quality hypergraph without requiring external knowledge. Then, we model diverse higher-order interactions and enhance representation learning based on the hypergraph mixture of experts and cross-view representation fusion. Extensive experiments on four real-world multi-domain datasets have shown that our HMoRec achieves significant performance gains.

Deep learning based diagnosis prediction from Electronic Health Record (EHR) data has demonstrated strong performance but remains hindered by limited interpretability, reducing its clinical applicability. Existing multi-agent frameworks attempt to address this challenge; however, they often rely on superficial, semantics-only predictions from a large language model (LLM) or adopt multi-classification heads, thereby inheriting the opacity of conventional deep learning approaches. We introduce DMAP, a multi-agent framework designed to enhance EHR modeling through structured collaboration and interpretable decision-making. Inspired by multidisciplinary clinical workflows, DMAP employs three types of agents: DeepL Agents, a Leader Agent, and a Critical Agent, which work together to analyze patient data and generate reliable reports. DeepL Agents process structured EHR inputs, model outputs, and interpretability signals to provide initial clinical evaluations. Leader Agent coordinates these insights through iterative discussions, synthesizing consensus-driven disease predictions and draft report. Critical Agent evaluates the medical soundness of the draft report, identifying gaps or inconsistencies. When uncertainty arises, a retrieval-augmented generation (RAG) module integrates medical knowledge to support final decisions. By simulating expert collaboration and integrating structured reasoning with external knowledge, DMAP delivers reliable, interpretable predictions and reports. Extensive experiments on two EHR datasets demonstrate its superior performance in disease prediction and report generation, highlighting its potential to advance clinical decision support through explainable and adaptive multi-agent collaboration.

Electronic Health Records (EHRs) offer rich longitudinal data for clinical prediction, but existing deep models struggle to jointly capture semantic richness and hierarchical structure. We propose RQCare, a novel framework that integrates semantic and structural information for interpretable hierarchical disease representation learning. RQCare consists of three components: (1) a Disease Embedding Residual Quantization module that learns discrete, interpretable hierarchies from embeddings; (2) a Dual-Graph Structure Learning module that refines representations using both patient-disease interactions and ICD hierarchy; (3) a GRU-based temporal model with attention for next-visit prediction. Evaluated on MIMIC-III and MIMIC-IV, RQCare outperforms state-of-the-art baselines, achieving up to 6.06% and 2.84% gains in Precision@10, respectively.

Accurate diagnosis prediction using Electronic Health Records (EHRs) is essential for personalized healthcare. Clinical knowledge graphs (KGs) can enrich EHRs by structuring medical knowledge, and recent work integrates large language models (LLMs) with KGs to enhance reasoning. However, these approaches often depends on static, expensive global graph construction and one-time retrieval, yielding noisy or irrelevant subgraphs that hinder effective diagnosis prediction in real-world clinical scenarios. To this end, we propose$\mathrm{D}^{2}$KGMed, a diagnosis prediction framework that constructs a patient-specific Dynamic Diagnostic Knowledge Graph guided by LLMs. It consists of two stages: constructing an initial graph from diagnostic entities and multi-source medical knowledge; refining its construction via supervised fine-tuning to better align with the ideal graph for conciseness and relevance, and subsequently leveraging it for interpretable predictions. This design reduces graph construction costs and retrieval noise common in KG+LLM methods, enabling more accurate diagnosis prediction. Extensive experiments on two real-world EHR datasets demonstrate that D2KGMed outperforms state-of-the-art baselines, especially in few-shot learning scenarios, showcasing its practical utility in real-world clinical settings.

Accurate user profiles are crucial for personalized recommendation systems to mitigate information overload on large-scale online platforms. While recent advances in large language models have enhanced semantic understanding for profile construction through textual artifacts, existing methods often neglect the higher-order structural patterns inherent in user-item interaction graphs-a key limitation for achieving accurate and diverse recommendations. In this paper, we propose SSPRec, a Higher-order Structure and Semantics-enhanced User Profiling for Recommendation. Specifically, we first introduce a multi-hop proximity matrix over item-item transitions, followed by low-rank approximation and clustering to group users based on behavioral similarity. Group-level user profiles are then distilled via representative keywords extracted from co-interacted items, and collaborative embeddings are concurrently learned from the interaction graph. To integrate collaborative signals with language-based profiles, we introduce a cross-view contrastive objective that encourages coherence between structural and semantic representations. Final recommendations are made using a fused user-item similarity score. Extensive experiments on four real-world datasets show that SSPRec not only outperforms baselines in accuracy (with 46.35% improvements), but also remains diverse and robust, even under incomplete interactions.

Language Models (LMs) have advanced diagnosis prediction by leveraging the semantic understanding of medical concepts in Electronic Health Records (EHRs). Despite these advancements, existing LM-based methods often fail to capture the structures of medical concepts (e.g., hierarchy structure from domain knowledge). In this paper, we propose BoxLM, a novel framework that unifies the structures and semantics of medical concepts for diagnosis prediction. Specifically, we propose a structure-semantic fusion mechanism via box embeddings, which integrates both ontology-driven and EHR-driven hierarchical structures with LM-based semantic embeddings, enabling interpretable medical concept representations. Furthermore, in the box-aware diagnosis prediction module, an evolve-and-memorize patient box learning mechanism is proposed to model the temporal dynamics of patient visits, and a volume-based similarity measurement is proposed to enable accurate diagnosis prediction. Extensive experiments demonstrate that BoxLM consistently outperforms state-of-the-art baselines, especially achieving strong performance in few-shot learning scenarios, showcasing its practical utility in real-world clinical settings.

Loan default prediction is a crucial component of risk management in financial loan services. In practice, significant monetary losses often stem from initially creditworthy loans that later default unexpectedly. This phenomenon arises because such loans, while assessed as low-risk at disbursement initially, have a high default-intention to arise, in a delayed manner, at an indeterminate time during the repayment period after disbursement. We term such default-intention as Delayed Defaultintention. In this paper, we present a new and pressing task, namely, Delayed Default-intention based Default prediction ($\mathrm{D}^{3}$), which is of practical significance but has been rarely studied in prior research. The core challenge of$D^{3}$task lies in its farsighted inference of delayed default-intention, as it does not manifest immediately after disbursement. To address this, we propose a survival analysis framework for the$\mathrm{D}^{3}$task and a novel RW-D${ }^{3}$method, which models the repayment willingness (RW) in a loan as a negatively correlated alternative to delayed default-intention. RW-D${ }^{3}$systematically initializes, dynamizes, and recovers the original RW representations based on user behavior sequences, enhancing their predictive capacity from a short-term to a long-term perspective. Additionally, RW-D${ }^{3}$provides a comprehensive prediction of defaults triggered by delayed default-intention by jointly considering repayment status and timing. Extensive experiments demonstrate the superiority of RW-D${ }^{3}$over state-of-the-art methods in both its predictive effectiveness and explainability in financial loan services.

Combinatorial Medication Recommendation (CMR) based on multimodal Electronic Health Records (EHRs) is a promising yet challenging frontier in AI-driven healthcare. Existing approaches usually rely on feature extraction from individual modalities without explicitly aligning information across different data sources. As a result, they may ignore complementary information from other modalities, leading to suboptimal representations for CMR. To this end, we propose MedAlign, a novel combinatorial Medication recommendation framework with multi-modality Alignment. Specifically, we first design a distribution-aware multimodal medication alignment module. This aligns distinct modality distributions of medications within a unified latent space, generating consistent medication representations. Furthermore, we introduce a longitudinal multi-view patient aggregation module, which aggregates the historical visits of patients with multi-view information to form informative patient representations. Finally, we propose a combinatorial medication recommendation module, enabling an accurate and safe medication recommendation combination for each patient. Extensive experiments on two real-world multimodal EHR datasets demonstrate the effectiveness of our MedAlign.

Stock movement prediction serves an important role in quantitative trading. Despite advances in existing models that enhance stock movement prediction by incorporating stock relations, these prediction models face two limitations, i.e., constructing either insufficient or static stock relations, which fail to effectively capture the complex dynamic stock relations because such complex dynamic stock relations are influenced by various factors in the ever-changing financial market. To tackle the above limitations, we propose a novel stock movement prediction model ECHO-GL based on stock relations derived from earnings calls. ECHO-GL not only constructs comprehensive stock relations by exploiting the rich semantic information in the earnings calls but also captures the movement signals between related stocks based on multimodal and heterogeneous graph learning. Moreover, ECHO-GL customizes learnable stock stochastic processes based on the post earnings announcement drift (PEAD) phenomenon to generate the temporal stock price trajectory, which can be easily plugged into any investment strategy with different time horizons to meet investment demands. Extensive experiments on two financial datasets demonstrate the effectiveness of ECHO-GL on stock price movement prediction tasks together with high prediction accuracy and trading profitability.

Multimedia recommender systems (MRS) become prevalent due to their rich multimodal data (e.g., visual and textual content). Recent advancements have leveraged Graph Neural Networks (GNNs) to integrate these data, they often fall short in capturing the complex high-order relations within multimodal data, but readily hypergraph structures are not always available. To this end, we introduce the HMRec framework, a novel approach in Heterogeneous Hypergraph Structure Learning tailored for MRS. Specifically, we formulate the construction of a heterogeneous hypergraph as determining item associations across modalities, and introduce an adaptive hypergraph convolution mechanism for differentially weighting multimodal hyperedges. Furthermore, we propose an enhanced multimedia recommendation module, which introduces a contrastive fusion mechanism to effectively integrate graph-view, hypergraph-view, and ID-specific embeddings. Extensive experiments on real-world multimodal datasets show the superiority of our proposed HMRec framework in offering great potential for multimedia recommendations over the state-of-the-art baselines regarding the Recall and NDCG metrics.

Continuous diagnosis prediction based on multi-modal electronic health records (EHRs) of patients is a promising yet challenging task for AI in healthcare. Existing studies ignore abundant domain knowledge of diseases (e.g., specific medical terms and their interrelations) in textual EHRs, which fails to accurately predict disease progression and assist in sequential diagnosis prediction. To this end, we first propose an Expert enhanced neural Ordinary Differential Equations (ExpertODE) framework for continuous diagnosis prediction. In particular, we first propose a novel Mixture of Language Experts (MoLE) module to enhance disease embeddings with domain knowledge. Furthermore, we propose a Contrastive Neural Ordinary Differential Equation (CNODE) module to continuously model temporal correlations of disease progression, and implement a unified contrastive learning framework to jointly optimize the domain-based MoLE module and the temporal-based CNODE module. Extensive experiments on two real-world textual EHR datasets show significant performance gains brought by our ExpertODE, yielding average improvements of 3.91% for diagnosis prediction over state-of-the-art competitors.

Semi-supervised graph domain adaptation, as a subfield of graph transfer learning, seeks to precisely annotate unlabeled target graph nodes by leveraging transferable features acquired from the limited labeled source nodes. However, most existing studies often directly utilize graph convolutional networks (GCNs)-based feature extractors to capture domain-invariant node features, while neglecting the issue that GCNs are insufficient in collecting complex structure information in graph. Considering the importance of graph structure information in encoding the complex relationship among nodes and edges, this paper aims to utilize such powerful information to assist graph transfer learning. To achieve this goal, we develop a novel framework called HOGDA. Concretely, HOGDA introduces a high-order structure information mixing (HSIM) module to effectively capture abundant structure information in graph, greatly enhancing the feature extractor's ability to adapt across different domains. Moreover, to achieve fine-grained feature distributions alignment, a novel strategy called adaptive weighted domain alignment (AWDA) is proposed to dynamically adjust the node weight during adversarial domain adaptation process, effectively boosting the model's transfer ability. Furthermore, to mitigate the overfitting phenomenon caused by limited source labeled nodes, we also design a trust-aware node clustering (TNC) strategy to guide the unlabeled nodes to achieve discriminative clustering. Extensive experimental results show that our HOGDA outperforms the state-of-the-art methods on various transfer tasks.

Personalized diagnosis prediction based on electronic health records (EHR) of patients is a promising yet challenging task for AI in healthcare. Existing studies typically ignore the heterogeneity of diseases across different patients. For example, diabetes can have different complications across different patients (e.g., hyperlipidemia and circulatory disorder), which requires personalized diagnoses and treatments. Specifically, existing models fail to consider 1) varying severity of the same diseases for different patients, 2) complex interactions among syndromic diseases, and 3) dynamic progression of chronic diseases. In this work, we propose to perform personalized diagnosis prediction based on EHR data via capturing disease severity, interaction, and progression. In particular, we enable personalized disease representations via severity-driven embeddings at the disease level. Then, at the visit level, we propose to capture higher-order interactions among diseases that can collectively affect patients’ health status via hypergraph-based aggregation; at the patient level, we devise a personalized generative model based on neural ordinary differential equations to capture the continuous-time disease progressions underlying discrete and incomplete visits. Extensive experiments on two real-world EHR datasets show significant performance gains brought by our approach, yielding average improvements of 10.70% for diagnosis prediction over state-of-the-art competitors.

Financing needs exploration (FNE), which explores financially constrained small- and medium-sized enterprises (SMEs), has become increasingly important in industry for financial institutions to facilitate SMEs’ development. In this paper, we first perform an insightful exploratory analysis to exploit the transfer phenomenon of financing needs among SMEs, which motivates us to fully exploit the multi-relation enterprise social network for boosting the effectiveness of FNE. The main challenge lies in modeling two kinds of heterogeneity, i.e., transfer heterogeneity and SMEs’ behavior heterogeneity, under different relation types simultaneously. To address these challenges, we propose a graph neural network named Multi-relation tRanslatIonal GrapH aTtention network (M-RIGHT), which not only models the transfer heterogeneity of financing needs along different relation types based on a novel entity—relation composition operator but also enables heterogeneous SMEs’ representations based on a translation mechanism on relational hyperplanes to distinguish SMEs’ heterogeneous behaviors under different relation types. Extensive experiments on two large-scale real-world datasets demonstrate M-RIGHT’s superiority over the state-of-the-art methods in the FNE task.