[Contact][Google Scholar]

What's New

---

2024

• [Nov. 28, 2024] Our paper "TeMatch: a fast temporal subgraph matching framework with temporal-aware subgraph matching algorithms" has got acccepted by ICDE 2025.
• [Nov. 25, 2024] Got invited to serve as a PC member/reviewer of DASFAA 2025 (research track).
• [Nov. 17, 2024] Our paper "Graph Triple Attention Networks: A Decoupled Perspective" has got accepted by KDD 2025.
• [Nov. 17, 2024] Our paper "Building Robust and Trustworthy HGNN Models: A Learnable Threshold Approach for Node Classification" has got accepted by ACM TKDD.
• [October 10, 1024] Our paper "Unsupervised Pre-Trained Social Networks for E-Commerce Community Detection" gets accepted by IEEE HPCC 2024.
• [August 20, 2024] Our preprint entitled "Graph Retrieval-Augmented Generation: A Survey" is online in arxiv. Welcome your valuable comments!
• [August 17, 2024] Our paper "DiVerFed: distribution-aware vertical federated learning for missing information" won the Best Student Paper Award from KSEM 2024.
• [July 28, 2024] Just finished an invited talk at CCF Computility 2024, Changchun, China, 2024.
• [July 08, 2024] Got invited to be a Reviewer of KDD 2025 (research track).
• [May 27, 2024] Two papers (GraphRPM: Risk Pattern Mining on Industrial Large Attributed Graphs; Subgraph Retrieval Enhanced by Graph-Text Alignment for Commonsense Question Answering) have got accepted by ECML PKDD 2024
• [May 17, 2024] Got elected to be Executive Director of Zhejiang Federation of Artificial Intelligence.
• [May 14, 2024] Our paper "DiVerFed: Distribution-Aware Vertical Federated Learning for Missing Information" has got accepted by KSEM 2024.
• [April 25, 2024] Got invited to be a program committee member of CIKM 2024 (applied research track).
• [April 16, 2024] Our paper "TeGraph+: scalable temporal graph processing enabling flexible edge modifications" has got accepted by IEEE TPDS.
• [Mar 18, 2024] Our paper "GraphGen: a distributed graph sample generation framework on industry-scale graphs" has got accepted by EuroSys 2024 poster track.
• [Mar 18, 2024] Got invited to serve as a programm commitee in ECML-PKDD 2024.
• [Mar 18, 2024] Got invited to serve as a program commitee in APWeb-WAIM 2024.
• [Mar 02, 2024] Our paper "TEA+: a novel temporal graph random walk engine with hybrid storage architecture" has got accepted by ACM TACO.
• [Feb 29, 2024] Got appointed as an Industry Mentor in the Institute of Software, Chinese Academy of Sciences.
• [Jan 19, 2024] Got invited to serve as a Reviewer for ADMA 2024.
• [Jan 17, 2024] Got invited to serve as a Reviewer for KDD 2024 research track.

2023

• [Dec 19, 2023] Finished an invited talk in 全国智能计算标准化工作组图计算研究组 workshop, 2023.
• [Dec 16, 2023] Finished an invited talk at ACM SIGOPS ChinaSys 2023.
• [Dec 09, 2023] Our paper "Integer is Enough: When Vertical Federated Learning Meets Rounding" got accepted by AAAI 2024.
• [Sep 22, 2023 Our paper "AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference as Preconditioning Matrix" got accepted by NeurIPS 2023.
• [Sep 12, 2023] Got invited to serve as a program committee member in 2024 SIAM International Conference on Data Mining (SDM 2024).
• [Sep 11, 2023 Our "Large Graph Model (LGM)" concept and research has been reported by multiple famous medias in China, including 凤凰网, 环球网, 新华财经, 今日头条, 搜狐, and CSDN
• [Sep. 05, 2023] Got invited to serve as a program committee member in 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024>).
• [August 05, 2023 Our paper "FAF: a risk detection framework on industry-scale graphs" has got accepted by CIKM 2023.
• [August 02, 2023] Our paper "G-Sparse: compiler-driven acceleration for generalized sparse computation for graph neural networks on modern GPUs" has got accepted by PACT 2023.
• [July 03, 2023] We are organizing a competititon with ICDM 2023 workshop ISDA, entitled "Pretrained Model-based Community Detection and Fraudulent Group Mining". Welcome to participate.
• [May 17, 2023] Our paper "Sharpness-aware minimization revisited: weighted sharpness as a regularization term" has got accepted by KDD 2023 (research track).
• [May 09, 2023] Got invited to serve as a program commiteee member in 19th International Conference on Advanced Data Mining and Applications (ADMA 2023).
• [April 23, 2023] Just served as a session chair in 28th International Conference on Database Systems for Advanced Applications (DASFAA 2023).
• [March 23, 2023] Our paper "GPC: compiler-based optimization for sparse computations in graph neural networks" has got accepted by EuroSys 2023 (poster track).
• [Feburary 05, 2023] I have got invited to serve as a Reviewer of SIGKDD 2023.
• [January 25, 2023] Our paper "Multi-Aspect Heterogeneous Graph Augmentation" has been accepted by WWW 2023 (Research track).
• [January 16, 2023] The Software Copyright Certificate of GeaLearning (a large-scale distributed graph learning system) has got issued in China.
• [January 03, 2023] I will serve as a program committee member in HiCOMB 2023.

2022

• [November 29, 2022] I will server as a program committee member in DASFAA 2023.
• [August 11, 2022] Our paper "TEA: a general-purpose temporal graph random walk engine" has been accepted by EuroSys 2023.
• [July 27, 2022] Our project won Annual T-STAR Data Intelligence Award of Ant Group.
• [June 23, 2022] The code of TeGraph has been released by our co-authors: https://github.com/huanzhizun/TeGraph.
• [June 22, 2022] Our paper " T-GCN: a sampling based streaming graph neural network system with hybrid architecture" has got accepted by PACT 2022.
• [June 14, 2022] Our project won Annual SuperMA Award of Ant Group in 2022.
• [May 13, 2022] Our paper "Bring orders into uncertainty: enabling efficient uncertain graph processing via novel path sampling on multi-accelerator system" has been accepted by ICS 2022.

2021

• [Nov. 18, 2021] Our paper "TeGraph: a novel general-purpose temporal graph computing engine" has got accepted by ICDE 2022. TeGRAPH is the first general- purpose temporal graph computing engine for efficiently pro- cessing temporal path problems and their applications. This engine can achieve significant speedups over the state-of-the-art designs with up to two orders of magnitude (241×) with the throughput of two hundred million edges per second.
• [Sep. 26, 2021] Ant Group's large-scale graph computing system GeaGraph gets recognized as World's Leading Internet Scientific and Technological Achievement at World Intenet Conference 2021 (WIC 2021). I am very happy to be a core team member of GeaGraph.
• [Sep. 01, 2021] Our paper Heterogeneous graph neural architecture search got accepted by ICDM 2021, Auckland, New Zealand.
• [June 19, 2021] Our paper "Adaptive Optimizers with Sparse Group Lasso for Neural Networks in CTR Prediction" get accepted by ECML-PKDD 2021.
• [June, 17, 2021] Our paper "Taking the Pulse of Financial Activities with Online Graph Processing" get published online in ACM SIGOPS Operating Systems Review
• [May, 20, 2021] Won the championship on the Stanford University Open Graph Benchmark proteins dataset leaderboard: https://ogb.stanford.edu/docs/leader_nodeprop/#ogbn-proteins.
• [May 12, 2021] Our graph learning system paper won the Annual Best Paper Award in Ant Group. Moreover, this system was listed in 2020 Ant Technology Memorabilia (2020年蚂蚁技术大事记).
• [Apr. 15, 2021] Our paper "Path-based Deep Network for Candidate Item Matching in Recommenders“ has got accepted by SIGIR 2021 as a full-paper.
• [Jan. 12, 2021] A US patent has got granted: "Vehicle accident image processing method and apparatus".
• [Jan. 11, 2021] A TW patent has got granted: "Method, device and equipment for updating convolutional neural network using GPU cluster".

2020

• [Dec. 17, 2020] Our work "Model-based cost estimation and its application in deep learning operation optimizations" got presented in GTC 2020, China.
• [Sep. 01, 2020] A new patent got granted: Model-based prediction method and device.
• [August 12, 2020] Our preliminary research on learning-to-compiling for deep learning is avaiable now: Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations.
• [June 30, 2020] A China patent has got granted: Method and device for detecting damage of article and article damage detector.
• [June 09, 2020] A China patent has got granted: "Chip and data processing method based on chip".
• [April 30, 2020] My first U.S. patent has got granted: "Fast computation of a convolutional neural network".

2019

• [December 31, 2019] Awarded Hangzhou 521 Program for Global Talents Introduction: Innovative Talent in Artificial intelligence
• [November 4, 2019] We will present "Woodpecker-DL: an efficient compiler for accelerating deep learning on heterogeneous computing architectures" at GPU Technology Conference 2019 (GTC 2019), Suzhou, China.
• [September 10, 2019] Our work "Woodpecker-AutoSearch: a machine learning-based framework for math kernel optimizations" will be presented at the DAWN retreat by Stanford University, 2019.

2017

• [July 06, 2017] I started working at Ant Financial as a senior technical expert to develop parallel machine learning algorithms and heterogeneous computing systems/platforms for artificial intelligence finance.
• [March 09, 2017] delivered an invited talk at Binghamton University (State University of New York at Binghamton), Binghamton, USA, 03/2017
• [January 20, 2017] delivered an invited talk at Fairfield University, Fairfield, USA, 01/2017
• [January 13, 2017] delivered an invited talk at Seven Bridges Genomics (a biomedical data analysis company accelerating breakthroughs in genomics research for cancer, drug development and precision medicine), Boston, USA

2016

• [December 20, 2016] Our extended LightSpMV paper, entitled "LightSpMV: faster CUDA-compatible sparse matrix-vector multiplication using compressed sparse rows", gets accepted by Journal of Signal Processing Systems.
• [November 10, 2016] I will be officialy listed in the 71st edition of Who's Who in America.
• [November 04, 2016] I released my Research Statement for Assistant Professorship Application (2016) publicly in ResearchGate. I believe that the themes and topics that I am planning to investigate in the future could be interesting to you! Click here to visist the research statement and welcome any feedback!
• [October 24, 2016] I got nominated to be listed in the 71st edition of Who's Who in America, for which Marquis states in the Preface that Who's Who in America "endeavors to profile the leaders of American society; those men and women who are influencing their nation's development" [Wiki].
• [August 30, 2016] I released my first OpenGraphAssembly white paper that was originally submitted to apply for Research Scientist Development Grants of Georgia Tech in June 2015. I will release more and more white papers in the future and share my thoughts with researchers from related community.
• [August 22, 2016] Our MSAProbs-MPI paper gets accepted by the Bioinformatics journal. The software is publicly available at here.
• [August 14, 2016] Our paper "Parallel pairwise correlation computation On Intel Xeon Phi clusters" get accepted by SBAC-PAC 2016 conference. The corresponding software LightPCC is available at here.
• [August 1, 2016] Our SNVSniffer 2.0 paper gets published online in the BMC Systems Biology paper.
• [July 17, 2016] Our "Kmerind: A flexible parallel library for k-mer indexing of biological sequences on distributed memory systems" paper gets accepted by ACM-BCB 2016.
• [May 26, 2016] NVIDIA has agreed to sponsor a Best GPU Paper/Talk Award for our WACEBI 2016 workshop. They will donate a GeForce GTX Titan X graphics card as the prize. Welcome to submit your high-quality papers to our workshop!
• [May 18, 2016] Our paper entitled"SNVSniffer: an integrated caller for germline and somatic single-nucleotide and indel mutations" get accepted by BMC Systems Biology. The software tool is publicly available at here.
• [May 13, 2016] Awarded The Program to Empower Partnerships with Industry (PEPI) Award from the South Big Data Regional Innovation Hub, USA, 2016.
• [May 05, 2016] The pre-print of our paper "Parallel Pairwise Correlation Computation On Intel Xeon Phi Clusters" is made available at arXiv for public review before formal submission to a journal/conference.
• [May 02, 2016] MSAProbs-MPI gets released online. By using distributed-memory systems, we manage to overcome high memory overhead barriers for multiple alignment of thousands of protein sequences. By scaling with hundreds of cores, we can reach faster speed.
• [April 17, 2016] Because of the very long peer-review time, I decided to make the LightScan (parallel scan primitives on CUDA-enabled GPUs) preprint publicly available at arXiv. Welcome any feed about this pre-print!
• [March 20, 2016] As the first news of the year, our SNVSniffer 2.0 gets released today! The paper has been submitted to a journal for peer review. Welcome any feed back about this software! Currently, only statically linked executable binary is available and the source code will be released some time later.

2015

• [December 29, 2015] Our SNVSniffer paper for germline and somatic variant calling has got published online.
• [December 07, 2015] Our CUSHAW3-UPC paper has got accepted by PLOS One.
• [November 20, 2015] We are happy to see that our Musket error correction algoirthm is used to assemble and annotate the genome of the UCSC mascot Ariolimax dolichophallus (i.e. the slender banana slug). Refer to the bottom of the page.
• [November 06, 2015] Our paper entitled "Bit-parallel approximate pattern matching: Kepler GPU versus Xeon Phi" has been published online.
• [November, 02, 2015] Our GPU-accelerated Wu-Manber algorithm gets accepted by the Parallel Computing journal.
• [October 09, 2015] The new CUDA-MEME 3.0.16 gets released, where we have fixed a bug that causes memory segmentation when using multiple threads for the EM stage.
• [September 13, 2015] Our open-source software CUSHAW3-UPC has got released. This software is a parallel and scalable NGS short-read aligner using the UPC++ parallel programming language and has been extensively tested on a compute cluster with 2048 CPU cores. Welcome any suggestions and comments!
• [September 08, 2015] Awarded the NVIDIA Academic hardware grant that donates one GeForce GTX TITAN X graphics card to support my research.
• [September 07, 2015] Our SNVSniffer paper for the calling of SNPs and somatic variants gets accepted by IEEE BIBM 2015.
• [September 01, 2015] One paper gets accepted by the IEEE ICCABS 2015 conference.
• [July 29, 2015] Our LightSpMV paper just won the Best Paper Award from the prestigious IEEE ASAP 2015 conference
• [May 16, 2015] Our CUDA-based LightSpMV paper for Sparse Matrix-Vector Multiplication has been accepted by IEEE ASAP 2015.
• [May 08, 2015] Our ParaBWT paper has been published online.
• [April 22, 2015] Our paper "Parallel and Space-efficient Construction of Burrows-Wheeler Transform and Suffix Array for Big Genome Data" has been accepted by IEEE TCBB.
• [March 25, 2015] We have removed the dependency on CUDA SDK in CUDASW++.
• [March 16, 2015] Our poster, named "Faster Compressed Sparse Row (CSR)-based Sparse Matrix-Vector Multiplication using CUDA", has been published online in GTC 2015.
• [Feburary 09, 2015] The source code of our SWAPHI software has been released!
• [Feburary 05, 2015] Get invited to act as a PC member of HiPC 2015 and PBC 2015.
• [January 23, 2015] Our GPU-based sparse matrix-vector multiplication (SpMV) algorithm has been accepted to present in GPU Technology Conference (GTC) 2015 as a poster. click here to download the poster.
• [January 19, 2015] Start working as a Research Scientist II (research faculty member) at Georgia Institute of Technology (USA).

2014

• [December 09, 2014] Our paper Bit-Parallel Approximate Pattern Matching on the Xeon Phi Coprocessor has been published online.
• [December 03, 2014] Our paper SWAPHI-LS: Smith-Waterman Algorithm on Xeon Phi coprocessors for Long DNA Sequences has been published online.
• [November 05, 2014] An improved version of SNVSniffer (v1.0.19) has been released. In this new version, we have introduced a new algorithm to estimate the purity of the tumor sample. This purity estimation algorithm works well on simulated normal-tumor samples through our evaluations.
• [October 04, 2014] Get invited to serve as a PC member for IPDPS 2015.
• [September 23, 2014] The first version of SNVSniffer, an integrated caller for germline and somatic SNVs, is online for public use and test now.
• [September 10, 2014] Our GSWABE paper has been published online.
• [August 21, 2014] An invited paper, named "GSWABE: faster GPU-accelerated sequence alignment with optimal alignment retrieval for short DNA sequences",  has just been accepted by Concurrency and Computation: Practice and Experience (impact factor 0.784).
• [July 31, 2014] Our All-Food-Seq paper has got published online at BMC Genomics.
• [July 24, 2014] Our All-Food-Seq (AFS) paper has just been accepted by BMC Genomics (impact factor 4.40).
• [June 30, 2014] The paper "SWAPHI-LS: Smith-Waterman Algorithm on Xeon Phi Coprocessors for Long DNA Sequences" has been accepted by IEEE Cluster 2014, and has also been recommended for Best Paper Award. Click here to download the open-source SWAPHI-LS software.
• [May 15, 2014] The paper "Faster GPU-Accelerated Smith-Waterman Algorithm with Alignment Backtracking for Short DNA Sequences" has got published online.
• [May 07, 2014] Our HECTOR paper gets published online by the BMC Bioinformatics journal.
• [April 26,2014] One solution to compile MSAProbs on Mac OS X has been given. Please refer to the project homepage for more details.
• [April 24, 2014] One co-authored paper, named "HECTOR: A parallel multistage homopolymer spectrum based error corrector for 454 sequencing data", gets accepted by the BMC Bioinformatics journal. The open-source software can be obtained from here.
• [April 23, 2014] I got invited to join the Program Committee of IEEE CloudCom 2014.
• [April 16, 2014] The original submission of the SWAPHI paper, to the IEEE ASAP 2014 conference, can be obtained from arXiv.
• [April 11, 2014] The SWAPHI paper has got accepted by ASAP 2014 as a 2-page short paper.
• [February 20, 2014] The CUSHAW software package (poster) will be presented in GPU Technology Conference 2014.
• [January 24, 2014] The CUSHAW3 paper has been published online.

2013

• [December 17, 2013] The CUSHAW3 paper, named "CUSHAW3: sensitive and accurate base-space and color-space short-read alignment with hybrid seeding", has got accepted by the PLOS ONE journal.
• [November 20, 2013] Have submitted my first DFG proposal as a principal investigator (PI). Took me about one month to finish the writing! EXCITED!
• [November 04, 2013] A book chapter named "Multiple protein sequence alignment with MSAProbs" gets published in the Methods in Molecular Biology book series (Springer).
• [October 11, 2013] Just fixed a bug of PASHA, which results in out-of-bound array accesses.
• [October 10, 2013] The CUSHAW2-GPU paper has already be published online.
• [October 05, 2013] The source code of CUSHAW3 has got released.
• [August 12, 2013] The SWAPHI (v1.0.4) software gets first released, which is the first parallelized Smith-Waterman protein database search algorithm on Intel Xon Phi coprocessors. The corresponding paper has been submitted.
• [July 23, 2013] The CUSHAW2-GPU paper has been accepted by IEEE Design & Test of Computers (entitled "CUSHAW2-GPU: empowering faster gapped short-read alignment using GPU computing").
• [June 22, 2013] The paper, entitled "Faster GPU-accelerated Smith-Waterman algorithm with alignment backtracking for short DNA sequences", has been accepted by the PBC 2013 workshop (in conjunction with PPAM 2013 conference in Poland).
• [June 20, 2013] A new version of PASHA (v1.0.9) got released. In this release, some changes have been made to significantly reduce the mis-assembly rate in scaffolds.
• [June 13, 2013] Just given an invited talk about PASHA at University of Cologne, Germany.
• [May 04, 2013] I got invited to join the Program Committee of ICPADS 2013.
• [May 03, 2013] The source code of CUSHAW2-GPU has been released.
• [April 18, 2013] The preprint paper for CUSHAW2 SOLiD color-space short-read alignment is available at arXiv.
• [April 04, 2013] CUDASW++ 3.0 paper has been published online by BMC Bioinformatics [PDF].
• [April 04, 2013] CUSHAW2 v2.4 gets released. We have incorporated some new features in this release, described as follows.
1. Different reference genome indexing from previous versions.
2. Support ABI SOLiD color-space single-end and paired-end/mate-paired alignment.
3. Improved base-space single-end and paired-end alignment quality.
4. Add a new option "-max_edit_dist" to allow users to specify the maximum edit distance of a reported alignment.
5. Each alignment in the SAM file has two tags given: NM (edit distance) and AS (alignment score).
• [April 02, 2013] CUDA-MEME v3.0.7 gets released. This version can be compiled using CUDA 5.0 toolkit, and automatically detects the maximum number of resident threads per multiprocessor on GPUs.
• [March 15, 2013] CUDASW++ 3.0 paper gets accepted by BMC Bioinformatics.
• [March 12, 2013] CUSHAW2-GPU was first released.