Services Conference Federation (SCF 2025)
http://icws.org/2025 , September 27 - 30, 2025, Hong Kong, China
Theme: Services Agents
SCF 2025 Advance Program
Room Locations:
Invited Plenary Sessions will be held in the Maggie Room on the 2nd floor.
Room A (as listed in the advance program) will also be located in the Maggie Room on the 2nd floor.
Room B (as listed in the advance program) will be in the Anita Room on the 2nd floor.
Registration Desk:
The registration desk will be located in front of the Maggie Room on the 2nd floor, and it will open at 8:00 a.m. (September. 27).
Please stop by to pick up your conference materials and name badge upon arrival.
For our conference participants only, a banquet will be held on the evening of September 27,2025. Further details about the event will be provided on-site.
Invited Plenary Sessions
Keynote 1: Dataflow-based High Efficient Graph Processing Accelerator
Saturday, September 27, 2025
8:50 - 9:50, UTC+8 Hong Kong, China
Keynote Speaker: Prof. Hai Jin, Huazhong University of Science and Technology
Abstract: With the rapid growth of big data, it is harder and harder to processing these ever-growing data with traditional computer architecture. Dataflow-based architecture provides a new way to tackle above challenge. This talk first briefly introduces the challenges in processing big data and also the difficulties in processing graph computing, then introduce some research results we have done during these years in using dataflow for graph computing. Finally, some future directions for dataflow architecture and also when used in graph computing are introduced.
About the Speaker
Hai Jin is a Chair Professor of computer science and engineering at Huazhong University of Science and Technology (HUST) in China. Jin received his PhD in computer engineering from HUST in 1994. In 1996, he was awarded a German Academic Exchange Service fellowship to visit the Technical University of Chemnitz in Germany. Jin worked at The University of Hong Kong between 1998 and 2000, and as a visiting scholar at the University of Southern California between 1999 and 2000. He was awarded Excellent Youth Award from the National Science Foundation of China in 2001.
Jin is a Fellow of IEEE, Fellow of CCF, and a life member of the ACM. He has co-authored more than 20 books and published over 900 research papers. His research interests include computer architecture, parallel and distributed computing, big data processing, data storage, and system security.
Keynote 2: Three Generations of Blockchain Technology: Whither Performance, Scalability, Energy Consumption and Fairness?
Saturday, September 27, 2025
9:50 - 10:50, UTC+8 Hong Kong, China
Keynote Speaker: Prof. Rudrapatna K. Shyamasundar, Indian Institute of Technology Bombay
Abstract: The introduction of Bitcoin, a peer-to-peer electronic cash system by Satoshi Nakamoto, was a milestone in the introduction of cryptocurrencies and blockchain technologies. It realized trust from untrusted stakeholders, thus revolutionizing the notion of trust. Bitcoin introduced the concept of a decentralized digital currency, enabling peer-to-peer transactions without intermediaries. Further, Bitcoin signalled out the blockchain data-structure having properties like public, immutable and distributed that are much sought after in complex societal systems. Bitcoin based on proof-of-work (PoW) consensus suffered from scalability, performance and large energy consumptions. Bitcoin being the champion introducer of cryptocurrencies and blockchain technologies epitomises the first generation blockchain technology. While several works tried to overcome the issues of PoW, there was the dire need of flexibility of programming transactions rather than confine to the primitive send /receive transactions available in the Bitcoin blockchain technology as that hindered innovations in blockchain technology applications. The introduction of smart contracts through programming languages like Go, DAML, Solidity etc., in the blockchain technology can be considered as the second generation blockchain technology. Ethereum platform with the rich smart contract specification language Solidity is treated as the one ushering the second generation blockchain technologies. Ethereum enriched innovations through the introduction of decentralized applications (Dapps). Initially Ethereum started with PoW as its consensus mechanism, realized flexibility to a large extent leading to a plethora of applications due to its rich smart contract language Solidity, but still suffered from the issues of scalability and high energy consumption. Recently, Ethereum has transitioned to proof-of-stake (PoS) consensus leading to a more scalable and less-energy consuming technology as compared to the version with PoW. However, it still suffers from issues of centralization, MEV attacks, attacks due to smart contract vulnerabilities and fairness.
While both the first and second generation blockchain technologies are characterized by pruning of branches of blocks based on the underlying consensus mechanisms a third generation blockchain technology has been introduced that does not prune any branch/transaction at all. Hedera built on Hashgraph consensus algorithm epitomizes this technology. Hedera assures a global order of all transactions and overcomes several of the issues highlighted.
In this talk, we discuss how characteristics of blockchain technologies like centralization, exploitation of smart contract vulnerabilities, MEV attacks, scalability, energy consumption and fairness have evolved with the generations of blockchain technologies. We further discuss issues of fairness in these technologies that has challenges for governance of blockchain technology applications.
About the Speaker
Rudrapatna K. Shyamasundar is a Life Fellow of IEEE, a Fellow of ACM, Distinguished ACM Speaker, a Distingusihed Alumnus of Indian Institute of Science, served as IEEE Distinguished Speaker, and the founding Dean of School of Technology and Computer Science at the Tata Institute of Fundamental Research (TIFR). He has been a JC Bose National Fellow at TIFR and IIT Bombay, currently he is an INAE (Indian National Academy of Engineering) Distinguished Professor at the Department of Computer Science, IIT Bombay where he has been directing the Centre of Excellence for Blockchain Research sponsored by Ripple, at IIT Bombay. He is an Adjunct Professor, NITIE (now IIM Mumbai), Mumbai and a Distinguished Fellow at IDRBT, Hyderabad.
He was awarded the 2014 SN Mitra award for excellence in research by the Indian National Academy of Engineering. Since 2015, he holds the distinguished position of Scholar-in-Residence at IIT Jodhpur and is a Distinguished Fellow at the Institute of Development and Research for Banking Technology (IDRBT). He was recently awarded the 2023 UBRI (University Blockchain Research Initiative from Ripple Inc) Educator Award in Toronto and the 2024 Outstanding Research Award from IFIP WG11.3 at DBSEC2024 in San Jose. He has more than 300 peer reviewed publications in Journals and proceedings, 8 patents, 8 books and guided more than 40 PhD students. He has been a visiting faculty at UIUC, UCSD at LA Jolla, IBM Research, Max Planck Inst, Japan Advanced Institute of Science and Technology (JAIST), Ericsson Fellow at University of Linkoping. He had also been an Adjunct Faculty at School of Computing at NUS, Singapore, had been invited Professor at the Technological University of St Petersburg, Russia, and Distinguished Fellow of the UK Royal Academy of Engineering at the Computer Group, University of Cambridge as well as City University of London. He also serves as an Adjunct Professor at IIM Mumbai. He has also been recently honoured with a Fellowship from British Blockchain Association (BBS).
He is a Fellow of Indian Academy of Sciences, Indian National Science Academy, National Academy of Sciences, National Academy of Engineering, India and a Fellow of the Academy of Sciences of the Developing world (TWAS), Trieste, Italy. He has also been recently conferred the Fellowship from the Asia-Pacific Artificial Intelligence Association (AAIA), Singapore.
He has/had been on the Governing Council of IIIT Allahabad, Indian Institute of Information Technology and Design Manufacturing at Jabalpur, CSIR-CMMACS (renamed CSIR Fourth Paradigm Institute) at Bangalore, Advisor for the COE of Union Bank of India. He serves on various DST, MEITY, SERB, UGC, AICTE, committees, and has been serving as WG member for Cyber Security at MEITY. He also serves/served on the research advisory boards of BSE and IDRBT and serves on the Board of Studies in computer science for various Universities. He served/serves on the IEEE Fellow selection committee on Product safety. He is also a recipient of Diamond Jubilee medal from IETE and also its’ Fellow and was also Chair of IEEE Computer Society section of Mumbai region between 2021-2022.
He has served on IEEE Esterel Standards Committee. He is serving as Editor-in-Chief for Sadhana- Journal of Engineering Sciences of the Indian Academy of Sciences for Computing and Data Sciences, Subject-Area Editor for IET Blockchain Journal McGraw Hill, and serves on the Editorial board of Journal of Parallel and Distributed Computing.
Keynote 3: TBD
Sunday, September 28, 2025
8:30 - 9:20, UTC+8 Hong Kong, China
Keynote Speaker: Prof. Kejiang Ye, Shenzhen Institutes of Advanced Technology
Abstract: Efficiently serving large-scale deep learning workloads, particularly large language models (LLMs) and inference services, remains a critical challenge in modern cloud clusters. These systems face two key problems: (1) underutilization of over-provisioned GPUs due to strict latency guarantees, and (2) dynamic request patterns and resource fragmentation in serverless environments. To address these issues, we present Mudi (EuroSys 2025) and FlexPipe (EuroSys 2026), two complementary systems that optimize GPU resource usage across inference and training workloads. Evaluation on real GPU cluster show the proposed methods achieve better resource efficiency as compared to state-of-the-art systems.
About the Speaker
Kejiang Ye is currently a Professor and the Director of the Research Center for Cloud Computing, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences. He received his B.S and Ph.D degree both from Zhejiang University and was a Post Doctoral Research Associate at Carnegie Mellon University (CMU). His research interests include Cloud Computing, Big Data and Industrial Internet. He is a Senior Member of IEEE and a Distinguished Member of China Computer Federation (CCF).
Keynote 4: BrokerChain Testnet: How We Design and What We Have Learned
Sunday, September 28, 2025
9:20 - 10:10, UTC+8 Hong Kong, China
Keynote Speaker: Prof. Huawei Huang, Sun Yat-sen University
Abstract: BrokerChain, a high-performance blockchain sharding protocol proposed by Prof. Huawei Huang's research group in 2022, addresses core challenges for blockchain sharding. In June 2025, his team launched BrokerChain’s testnet, which is a real-world example of public sharding blockchain. This testnet offers a research and development platform for academia and industry, supporting experiments in DeFi protocols, real-world assets (RWA) tokenization, and the integration between AI and Web3. Its core features include EVM compatibility, low gas fee consumption, high-efficiency intra-shard consensus, and user-friendly wallet software, significantly lowering barriers for developers and end-users. This talk delves into BrokerChain Testnet’s architectural design, technological innovations, and the findings through real-world running over the past few months. Through dual validation via technological innovation and ecosystem practice, BrokerChain testnet presents a comprehensive paradigm for the blockchain sharding, because its hierarchical consensus framework and native economic incentive mechanisms can provide insights for the development of Web3 infrastructure.
About the Speaker
Huawei Huang is a professor at Sun Yat-sen University, and a dual-appointment professor at the Hong Kong Advanced Research Institute (HKARI) of SYSU and at Lingnan College of SYSU. Since 2023, he has been consecutively recognized among the Top 2% Scientists Worldwide by Stanford University. His research interests include blockchain systems and protocols, blockchain finance, DeFi protocols, and Web3 infrastructure. He has published numerous research papers in CCF-A journals and conferences such as IEEE/ACM ToN, JSAC, TPDS, TSC, TDSC, TIFS, TMC, TC, and INFOCOM. He has served as chair for many academic conferences, workshops, and symposiums. He is the author of two blockchain monographs “From Blockchain to Web3 & Metaverse” and “Blockchain Scalability,” as well as a popular blockchain science book namely “From Blockchain to Web3: building the next-generation Internet”. Under his leadership, his team developed and open-sourced a blockchain experimental tool named BlockEmulator, which provides researchers with mature, high-quality experimental framework and code. BlockEmulator has served researchers ranging from over 90 countries and regions worldwide.
Keynote 5: An Intelligent Aided Diagnostic Method for Prostate Cancer Based on MRI Radiomics
Sunday, September 28, 2025
10:10 - 11:00, UTC+8 Hong Kong, China
Keynote Speaker: Prof. Mengxing Huang, Hainan University
Abstract: Prostate cancer has a high global incidence rate and is one of the major malignant tumors threatening men's health, the incidence rate and mortality rate of prostate cancer in the world rank the 2nd and 5th among male cancers respectively. MRI is currently recognized as the best imaging examination technology for prostate cancer. So combining medical imaging with artificial intelligence to realize automatic and interactive diagnosis of prostate cancer, this application has significant application value for the world's medical development. The report elaborates on the research progress of key technologies such as multimodal MRI image registration, annotation, segmentation, localization, and grading, providing a full chain of artificial intelligence technology for intelligent assisted diagnosis of prostate cancer. Meanwhile, the future development and issues of intelligent assisted diagnosis technology for prostate cancer were discussed.
About the Speaker
Mengxing Huang is a professor at Hainan University, and an Outstanding Talent of Hainan Province, Hainan Province Nanhai Famous Expert, Outstanding Expert with Outstanding Contributions in Hainan Province, Chief Scientist of National Key R&D Program Project, Member of the Artificial Intelligence and Blockchain Expert Committee of the Science and Technology Commission of the Ministry of Education, Executive Director of the Graduate Education Branch of the China Electronics Education Society, Chairman of the Hainan Automation Society, Chairman of the Hainan Province Electronic Information Professional Teaching Guidance Committee, and Chairman of the Hainan Province Electronic Information Discipline Evaluation Group; Deputy Leader and Expert Group Leader of the Planning Leadership Group for the Hainan Social Management Informatization Platform; Member of the Standing Committee of the Intelligent Fusion Special Committee and the Intelligent Aerospace System Special Committee of the Chinese Artificial Intelligence Society, member of the Information System Special Committee of the Chinese Computer Society; Editorial board member of the Journal of Communications. His main research areas include big data and intelligent information processing, multi-source information perception and fusion, artificial intelligence and intelligent services, etc. In recent years, Mengxing Huang has published over 230 SCI papers as the first author and corresponding author in Science, IEEE Transactions, Neural Networks, and other fields (including 2 ESI hot papers and 7 highly cited papers); Obtained 109 national authorized invention patents, 96 software copyrights, 6 group standards, and 4 provincial and ministerial level scientific and technological awards, including 1 first prize and 1 second prize of Hainan Provincial Science and Technology Progress Award as the first author; Published 5 monographs and translated 2 books, Hosted and undertaken more than 30 scientific research projects at all levels. Selected for the top 2% of global scientists in 2024.
Advance Program (version 20250922) — Download