湖南大学计算机学院张柏杨,全哲-湖大信息科学与工程学院

在研项目：

(1) 国家重点研发计划：基于国家高性能计算环境的教育实践平台(201607－201808)

(2) 国家重点研发计划：HPC教育实践软件支撑平台研发项目(201809－202108)

(3) 国家自然科学青年基金项目：基于SAT编码的最大团并行算法的设计、优化及其应用研究(201701－201912)

论文节选(近3年)：

[1] KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction. IJCAI 2020 (CCF A)

[2] Text to Image Synthesis with Bidirectional Generative Adversarial Network. ICME 2020 (CCF B)

[3] DeepGS: Deep Representation Learning of Graphs and Sequences for Drug-Target Binding Affinity Prediction. ECAI 2020 (CCF B)

[4] A Novel Model for Imbalanced Data Classification. AAAI 2020 (CCF A)

[5] Task Scheduling for Energy Consumption Constrained Parallel Applications on Heterogeneous Computing Systems. TPDS 2020. (CCF A)

[6]An Improved Hierarchical Datastructure for Nearest Neighbor Search. AAAI 2019 (CCF A)(

[7]Heavy-ball Algorithms Always Escape Saddle Points. IJCAI 2019 (CCF A

[8]Iteratively Reweighted Penalty Alternating Minimization Methods with Continuation for Image Deblurring. ICASSP 2019 (CCF B) (paper)

[9] GraphCPI: Graph Neural Representation Learning for Compound-Protein Interaction. BIBM 2019. (CCF B)

[10] A Novel Molecular Representation with BiGRU Neural Networks for Learning Atom. Briefings in Bioinformatics 2019. (CCF B) (paper)

[11] An efficient real-time data collection framework on petascale systems. NEUROCOMPUTING 2019. (SCI 2区) (paper)

[12] An Efficient Framework for Sentence Similarity Modeling. IEEE/ACM TASLP 2019. (CCF B) (paper)

[13] ACV-tree: A New Method for Sentence Similarity Modeling. IJCAI 2018. (CCF A) (paper)

[14] A System for Learning Atoms Based on Long Short-Term Memory Recurrent Neural Networks. BIBM 2018. (CCF B) (paper)

[15] ISAECC:An Improved Scheduling Approach for Energy Consumption Constrained Parallel Applications on Heterogeneous Distributed Systems. ICPADS 2018. (CCF C) (paper)

发明专利列表：

(1)基于知识图谱的图卷积药物对相互作用预测方法及系统. 202010216234.5

(2) 一种基于双向架构对抗生成网络的由文字生成图片的方法. 202010185829.9

(3) 一种基于深度学习的药物预测方法. CN111210878A

(4) 一种基于向量化的日志模板提取方法和系统. CN110175158A

(5) 一种基于Smi2Vec的BiGRU药物毒性预测模型的实现. CN110277173A

(6) 一种基于ARMv8 64位多核处理器的低精度矩阵乘法函数设计与实现方法. CN110782009A

(7) 面向高性能计算应用的通信特征模型方法及系统. CN110928705A

(8) 一种基于图卷积和词向量的药物-靶标相互作用预测方法. CN110289050A

(9) 一种将深度学习与数学分析相结合的句子分类改进方法. 2018108127742

(10) 一种基于词向量的句子相似度比较方法. 201711273188.7

(11) 一种基于深度学习的药物活性预测方法. CN109033738A

(12) 一种基于程序特征分析的迭代编译优化方法. 201711113109.6

(13) 一种基于大型系统拓扑结构的容错节点分配方法. 201711114201.4

软件著作权：

(1)高性能教育实践软件平台反馈式调试系统V1.0