Recent advances in large language models (LLMs) and text-aware graph learning have increased interest in reasoning over textattributed graphs (TAGs).In many real-world settings, such graphs are inherently heterogeneous, with most existing benchmarks remaining largely homogeneous in structure.As a result, the lack of large-scale benchmarks for heterogeneous text-attributed graphs has hindered systematic evaluation and fair comparison of existing methods.In this work, we introduce CITE -Catalytic Information Textual Entities Graph, the first and largest heterogeneous text-attributed citation graph benchmark for catalytic materials.CITE contains over 438K nodes and 1.2M edges spanning four node types and four relation types, with rich node-level textual information.We establish standardized evaluation protocols for node classification and link prediction, and conduct ablation studies to assess the impact of graph heterogeneity and textual attributes.Using CITE, we benchmark four classes of learning paradigms, including homogeneous graph models, heterogeneous graph models, LLM-centric models, and LLM+Graph models.By providing a largescale heterogeneous text-attributed benchmark together with standardized evaluation protocols and comprehensive baselines, CITE enables systematic assessment across diverse modeling paradigms and offers new insights into textaware and LLM-enhanced graph learning.The dataset 1 , codebase and evaluation suite 2 are publicly available.

In real-world scenarios, optimization problems generally exhibit multiobjective characteristics, necessitating a balance among conflicting evaluation criteria. An effective approach to multiobjective optimization (MOO) is to approximate the Pareto front. However, completely solving for the Pareto front incurs extremely high computational costs, making it almost infeasible in practical applications. In practical scenarios, decision makers (DMs) typically require only a single most preferred solution from the Pareto-optimal set. Existing optimization methods often struggle to incorporate real-time DMs' preferences during the optimization process. To address this limitation, this article proposes a preference-aware Bayesian optimization (PABO) framework for interactive decision-making that seamlessly integrates DMs' feedback throughout the entire optimization process. By embedding preference information into the candidate solution generation stage, PABO dynamically adjusts the balance between exploration of uncertain regions and exploitation of preference-aligned solutions, thereby achieving efficient preference satisfaction. Experiments on benchmark functions and real-world engineering cases demonstrate that PABO achieves comparable or superior solution quality with significantly fewer expensive evaluations than state-of-the-art methods. This achievement indicates that PABO demonstrates significant advantages in improving optimization efficiency and reducing costs, providing a more feasible technical approach for the practical application of MOO problems.

Automatic disease diagnosis from symptoms has attracted much attention in medical practices. It can assist doctors and medical practitioners in narrowing down disease candidates, reducing testing costs, improving diagnosis efficiency, and more importantly, saving human lives. Existing research has made significant progress in diagnosing disease but was limited by the gap between interpretability and accuracy. To fill this gap, in this paper, we propose a method called Reinforced Disease Diagnosis on Knowlege Graph (RDKG). Specifically, we first construct a knowledge graph containing all information from electronic medical records. To capture informative embeddings, we propose an enhanced knowledge graph embedding method that can embed information outside the knowledge graph into entity embedding. Then we transform the automatic disease diagnosis task into a Markov decision process on the knowledge graph. After that, we design a reinforcement learning method with a soft reward mechanism and a pruning strategy to solve the Markov decision process. We accomplish automated disease diagnosis by finding a path from symptoms to disease. The experimental results show that our model can effectively utilize heterogeneous information in the knowledge graph to complete the automatic disease diagnosis. Besides, our model demonstrates supreme performance in both accuracy and interpretability.

With the development of natural language processing tech- niques(NLP), automatic diagnosis of eye diseases using ophthalmology electronic medical records (OEMR) has become possible. It aims to evaluate the condition of both eyes of a patient respectively, and we formulate it as a particular multi-label classification task in this paper. Although there are a few related studies in other diseases, automatic diagnosis of eye diseases exhibits unique characteristics. First, descriptions of both eyes are mixed up in OEMR documents, with both free text and templated asymptomatic descriptions, resulting in sparsity and clutter of information. Second, OEMR documents contain multiple parts of descriptions and have long document lengths. Third, it is critical to provide explainability to the disease diagnosis model. To overcome those challenges, we present an effective automatic eye disease diagnosis framework, NEEDED. In this framework, a preprocessing module is integrated to improve the density and quality of information. Then, we design a hierarchical transformer structure for learning the contextualized representations of each sentence in the OEMR document. For the diagnosis part, we propose an attention-based predictor that enables traceable diagnosis by obtaining disease-specific information. Experiments on the real dataset and comparison with several baseline models show the advantage and explainability of our framework.

Drug-target interaction (DTI) prediction can identify novel ligands for specific protein targets, and facilitate the rapid screening of effective new drug candidates to speed up the drug discovery process. However, the current methods are not sensitive enough to complex topological structures, and complicated relations between multiple node types are not fully captured yet. To address the above challenges, we construct a metapath-based heterogeneous bioinformatics network, and then propose a DTI prediction method with metapath-based hierarchical transformer and attention network for drug-target interaction prediction (MHTAN-DTI), applying metapath instance-level transformer, single-semantic attention and multi-semantic attention to generate low-dimensional vector representations of drugs and proteins. Metapath instance-level transformer performs internal aggregation on the metapath instances, and models global context information to capture long-range dependencies. Single-semantic attention learns the semantics of a certain metapath type, introduces the central node weight and assigns different weights to different metapath instances to obtain the semantic-specific node embedding. Multi-semantic attention captures the importance of different metapath types and performs weighted fusion to attain the final node embedding. The hierarchical transformer and attention network weakens the influence of noise data on the DTI prediction results, and enhances the robustness and generalization ability of MHTAN-DTI. Compared with the state-of-the-art DTI prediction methods, MHTAN-DTI achieves significant performance improvements. In addition, we also conduct sufficient ablation studies and visualize the experimental results. All the results demonstrate that MHTAN-DTI can offer a powerful and interpretable tool for integrating heterogeneous information to predict DTIs and provide new insights into drug discovery.

Drug-drug interaction (DDI) prediction can discover potential risks of drug combinations in advance by detecting drug pairs that are likely to interact with each other, sparking an increasing demand for computational methods of DDI prediction. However, existing computational DDI methods mostly rely on the single-view paradigm, failing to handle the complex features and intricate patterns of DDIs due to the limited expressiveness of the single view. To this end, we propose a Hierarchical Triple-view Contrastive Learning framework for Drug-Drug Interaction prediction (HTCL-DDI), leveraging the molecular, structural and semantic views to model the complicated information involved in DDI prediction. To aggregate the intra-molecular compositional and structural information, we present a dual attention-aware network in the molecular view. Based on the molecular view, to further capture inter-molecular information, we utilize the one-hop neighboring information and high-order semantic relations in the structural view and semantic view, respectively. Then, we introduce contrastive learning to enhance drug representation learning from multifaceted aspects and improve the robustness of HTCL-DDI. Finally, we conduct extensive experiments on three real-world datasets. All the experimental results show the significant improvement of HTCL-DDI over the state-of-the-art methods, which also demonstrates that HTCL-DDI opens new avenues for ensuring medication safety and identifying synergistic drug combinations.

Convolutional neural networks (CNNs) have been proposed to be widely adopted to make predictions on a large amount of data in modern embedded systems. Prior studies have shown that convolutional computations which consist of numbers of multiply and accumulate (MAC) operations, serve as the most computationally expensive portion in CNN. Compared to the manner of executing MAC operations in GPU and FPGA, CNN implementation in the RRAM crossbar-based computing system (RCS) demonstrates the outstanding advantages of high performance and low power. However, the current design is energy-unbalanced among the three parts of RRAM crossbar computation, peripheral circuits and memory accesses, the latter two factors can significantly limit the potential gains of RCS. Addressing the problem of high power overhead of peripheral circuits in RCS, the Peripheral Circuit Unit (PeriCU)-Reuse scheme has been proposed to meet given power budget. In this paper, it is further observed that memory accesses can be bypassed if two adjacent layers are assigned in different PeriCUs. In this way, memory accesses can be reduced and thus the performance and power can be improved. A loop tiling technique is proposed to save memory accesses. The experiments of two convolutional applications validate that the proposed loop tiling technique can reduce energy consumption by 61.7%.

The massive data is constantly and rapidly growing in remote sensing field. How to achieve efficient storage and rapid retrieval of massive remote sensing image metadata is a difficult problem. Big Data technologies provide convenient and fast tools for the storage, retrieval and analysis of remote sensing image metadata. According to the feature of remote sensing image metadata, we first give new concepts of fat grid and thin grid and propose a grid indexing method called Spark-Fat-Thin-Grid-Index (SFTGridIndex). In SFTGridIndex, the index file and partitions files are stored in HDFS. We then design an optimized retrieval method based on SFTGrid-Index. The method can avoid the intersection computing of a large number of polygons. This research can ensure efficient storage and fast query of massive remote sensing image metadata and has good scalability.

BACKGROUND: Linkage analysis is the first step in the search for a disease gene. Linkage studies have facilitated the identification of several hundred human genes that can harbor mutations leading to a disease phenotype. In this paper, we study a very important case, where the sampled individuals are closely related, but the pedigree is not given. This situation happens very often when the individuals share a common ancestor 6 or more generations ago. To our knowledge, no algorithm can give good results for this case. RESULTS: To solve this problem, we first developed some heuristic algorithms for haplotype inference without any given pedigree. We propose a model using the parsimony principle that can be viewed as an extension of the model first proposed by Dan Gusfield. Our heuristic algorithm uses Clark's inference rule to infer haplotype segments. CONCLUSIONS: We ran our program both on the simulated data and a set of real data from the phase II HapMap database. Experiments show that our program performs well. The recall value is from 90% to 99% in various cases. This implies that the program can report more than 90% of the true mutation regions. The value of precision varies from 29% to 90%. When the precision is 29%, the size of the reported regions is three times that of the true mutation region. This is still very useful for narrowing down the range of the disease gene location. Our program can complete the computation for all the tested cases, where there are about 110,000 SNPs on a chromosome, within 20 seconds.

SaaS is a novel software model that data and applications of service are outsourced to service provider. Although SaaS model offers many benefits for small and medium enterprises, data privacy issue is the most challenge for the development of SaaS. In this paper we propose a new hybrid fragmentation approach which is different from traditional data encryption to protect data. We define three kinds of privacy constraints to support finger-grained privacy customization. We also give a heuristic hybrid fragmentation algorithm which considers query efficiency to produce a hybrid fragmentation. We make some experiments to analyze our approach in the paper.