DOCSLIB.ORG

Artificial Intelligence on Mobile Devices

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Artificial Intelligence on Mobile Devices Editorial Introduction to the Special Articles in This Issue Artificial Intelligence on Mobile Devices Qiang Yang, Feng Zhao n This issue of AI Magazine contains several n the film 2001: A Space Odyssey, a bulky computer system guest-edited articles devoted to some exemplary known as HAL captivated a generation of people with the works of AI on mobile devices. It includes four concept of artificial intelligence (AI) and intelligent works that range from mobile activity recogni - I machines. Today, as the world moves into one in which every - tion and air-quality detection to machine trans - lation and image compression one owns at least one mobile device, be it a smartphone, a tablet, or other handheld device, applications on the devices are increasingly more intelligent as well. Estimates put the global revenue for mobile apps at $150 billion dollars, 1 and mobile speech-recognition platforms will grow 68 percent through 2017 through cloud-based solutions, according to ABI Research. 2 We will see more and more applications of AI on the mobile devices. This special issue of AI Magazine is devoted to some exempla - ry works of AI on mobile devices. We include four works that range from mobile activity recognition and air-quality detection to machine translation and image compression. These works were chosen from a variety of sources, including the Interna - tional Joint Conference on Artificial Intelligence 2011 Special Track on Integrated and Embedded AI Systems, held in Barcelona, Spain, in July 2011. In “User-Centric Indoor Air-Quality Monitoring on Mobile Devices,” written by Yifei Jiang, Kun Li, Ricardo Piedrahita, Yun Xiang, Lei Tian, Omkar Mansata, Qin Lv, Robert P. Dick, Michael Hannigan, and Li Shang, the authors develop a novel and important technique for portable indoor air quality (IAQ) detec - Copyright © 2013, Association for the Advancement of Artificial Intelligence. All rights reserved. ISSN 0738-4602 SUMMER 2013 9 Editorial tion. They present their system MAQS, ing, which leads to a deliberation-intu - and Technology. His research interests are which uses a mobile-phone-based ition architecture to balance accuracy data mining and artificial intelligence indoor location tracking system to and energy efficiency. Focusing on trip including machine learning, planning, and determine the whereabouts of users. detection, the deliberation phase uses activity recognition. He is a Fellow of IEEE, IAPR, and AAAS. He received his Ph.D. from MAQS uses air-quality sensing devices sensors that provide information such the Computer Science Department of the as GPS and Wi-Fi data in a cell-ID-based to report on the quality measurements University of Maryland, College Park in for an individual or a group of people learning system, and the intuition 1989. He previously served as assistant, then in real time. This system demonstrates phase relies on the cell ID patterns to associate professor at the University of an integrated ability to locate users predict the start and end of a trip. The Waterloo from 1989–1995, and a professor based on Wi-Fi signals and to apply an system was tested on real-life mobile and NSERC Industrial Research Chair at air-exchange-rate-based IAQ method phone data over a long period of time, Simon Fraser University in Canada from 1995–2001. He was elected as a vice chair of using CO 2 sensors and a zone-based showing a large amount of energy sav - proximity detection method for ings and high accuracy and timeliness ACM SIGART in July 2010 and is the found - pulling the data from different sensors in intuitive trip detection. ing editor in chief of ACM Transactions on Intelligent Systems and Technology. Yang is on and phones together. The MAQS sys - In the final article, “Learning Com - the editorial board of IEEE Intelligent Systems pact Visual Descriptors for Low Bit Rate tem in particular tackles the important and has served as a program comittee issue of energy savings by allowing the Mobile Landmark Search,” Ling-Yu cochair and general cochair of several inter - different devices to share information. Duan, Jie Chen, Rongrong Ji, Tiejun national conferences. He serves on the IJCAI In “Speaking Louder than Words Huang, and Wen Gao consider a very Board of Trustees and will be the IJCAI pro - with Pictures Across Languages,” important problem of mobile-based gram chair for IJCAI 2015. Andrew Finch, Wei Song, Kumiko systems: how to transmit large images Tanaka-Ishii, and Eiichiro Sumita using low-bit mobile-based image Feng Zhao is an assistant managing director explore an iPad-based system for cross- search. The method that they employ at Microsoft Research Asia, where he over - language communication using pic - is clever: once a mobile user enters a sees multiple research areas including hard - tures. Their system allows users of one region, the server transmits a down - ware computing, mobile and sensing, soft - ware analytics, systems, and wireless and language to express their thoughts in a stream supervision to “teach” the networking. His own research has focused mobile device by linearly projecting sequence of picture icons, based on on networked embedded systems such as which they generate natural language the original high-dimensional image sensor networks, energy and resource man - in the native languages of the users of into a compact code book. Then, users’ agement of distributed systems as in data the system for verification of the user’s queries based on a high-dimensional centers and cloud computing, and mobile intention. Then, the system can trans - code-word histogram can be converted devices and mobility. He has also done work late the user’s sentences to another lan - to a compact histogram, which is trans - on parallel computing, fast N-body algo - guage based on the meaning of the pic - mitted for search and query. rithms, machine recognition, and diagnos - ture icons, completing the machine- The four articles in this special issue tics. Prior to Microsoft Research Asia, Zhao was a principal researcher at Microsoft translation process. This second chan - represent a cross section of work in the increasingly popular area of AI on Research Redmond, where he founded and nel of communication makes the managed the Networked Embedded Com - mobile devices. We can see that the AI machine-translation result more puting Group. The group has developed the robust. In addition, as the authors systems on mobile phones must con - MSR sensor mote, tiny Web Service, claim, the process of pointing and tap - sider a number of new issues and con - SenseWeb and SensorMap, Data Center ping on icons is a natural way of straints, including limited energy Genome, JouleMeter, and GAMPS data com - inputting on mobile devices. They resources, constrained communication pression. With the help of some of these implemented their idea in a system bandwidth, relatively small display technologies, today the Microsoft data cen - known as picoTrans, which is able to area, and emphasis on user interaction ters are among the most densely instru - predict the user’s intended expression models. In addition, it is necessary to mented and monitored cloud computing infrastructures in the world. Zhao received from the icon sequence most of the consider a number of other issues for AI systems on mobile phones, such as his Ph.D. in electrical engineering and com - time. This system not only shows the puter science from MIT, has taught at Stan - geographical information, location possibility of machine translation on ford University and Ohio State University, mobile devices, but also points at a new techniques, user studies, and comput - and currently also serves as an affiliate fac - way of natural interaction between er-human interaction. ulty member at the University of Washing - users and mobile devices. ton and an adjunct professor at Hong Kong University of Science and Technology. Zhao In “Thinking Fast and Slow: An Notes Approach to Energy-Efficient Human was a principal scientist at Xerox PARC and Activity Recognition on Mobile 1. See Strategy Analytics (www.strategyana - founded PARC’s research effort in sensor Devices,” Yifei Jiang, Du Li, and Qin Lv lytics.com). networks and distributed diagnostics. He served as the founding editor-in-chief of propose a two-phase approach to activ - 2. See ABI Research (www.abiresearch.com). ACM Transactions on Sensor Networks. An ity recognition for trip detection using Qiang Yang is the head of Huawei Noah’s IEEE Fellow and ACM Distinguished Engi - a mobile phone. The two-phase Ark Research Lab and a professor in the neer, he received a Sloan Research Fellow - approach applies a well-known theory Department of Computer Science and Engi - ship and NSF and ONR Young Investigator in psychology of human decision mak - neering, Hong Kong University of Science Awards. 10 AI MAGAZINE.
Load more

Recommended publications
  • Social Information Filtering
    Social Information Filtering Hang Li Noah’s Ark Lab Huawei Technologies 1 Talk Outline Huawei Noah’s Ark Lab Our Vision and Approach Social Information Filtering Weibo Robot 2 Huawei Noah’s Ark Lab Mission: ◦ Building “Noah’s Ark” to overcome the deluge of information Research Areas: ◦ Data Mining ◦ Machine Learning ◦ Natural Language Processing ◦ Information Retrieval ◦ Social Media ◦ Mobile Intelligence ◦ Human Computer Interaction Location: Hong Kong, Shenzhen, Beijing Established: June 2012 Our Vision Vision ◦ From Big Data to Deep Knowledge Goal ◦ Building intelligent assistants on mobile devices using big data on the cloud ◦ Passing Turing tests in specific domains 4 Our Approach Big Machine Learning ◦ Acquiring knowledge by large scale machine learning ◦ Example: Google, learning concept of cat from millions of images Human Computation ◦ Humans and machines jointly accomplish tasks ◦ Example: Univ. of Washington, solving large scale gene problem by leveraging human power Lifelong Learning ◦ Continuously accumulating knowledge by machine learning ◦ Example: CMU, NELL (Never Ending Language Learning) 5 Example: Intelligent Mobile Device Video 6 Two Challenges: Information Overload and Information Shortage 7 Social Information Filtering Valuable information is shared on social media Can get information by following key people Taking social media as information filter Building information assistant for each user or each group of users based on the ‘social information filter’ 8 Weibo Robot •Intelligent Information Assistant
    [Show full text]
  • Conference Digest
    Conference Digest 2015 IEEE International Conference on Mechatronics and Automation IEEE ICMA 2015 Beijing, China August 2 - 5, 2015 Cosponsored by IEEE Robotics and Automation Society Beijing Institute of Technology Kagawa University, Japan Technically cosponsored by The Institute of Advanced Biomedical Engineering System, BIT Intelligent Robotics Institute, Key Laboratory of Biomimetic Robots and Systems, Ministry of Education, BIT State Key Laboratory of Intelligent Control and Decision of Complex Systems, BIT Tianjin University of Technology Harbin Engineering University Harbin Institute of Technology State Key Laboratory of Robotics and System (HIT) The Robotics Society of Japan The Japan Society of Mechanical Engineers Japan Society for Precision Engineering The Society of Instrument and Control Engineers University of Electro-Communications University of Electronic Science and Technology of China Changchun University of Science and Technology National Natural Science Foundation of China Chinese Mechanical Engineering Society Chinese Association of Automation Life Electronics Society, Chinese Institute of Electronics IEEE ICMA 2015 PROCEEDINGS Additional copies may be ordered from: IEEE Service Center 445 Hoes Lane Piscataway, NJ 08854 U.S.A. IEEE Catalog Number: CFP15839-PRT ISBN: 978-1-4799-7097-1 IEEE Catalog Number (CD-ROM): CFP15839-CDR ISBN (CD-ROM): 978-1-4799-7096-4 Copyright and Reprint Permission: Copyright and Reprint Permission: Abstracting is permitted with credit to the source. Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923.
    [Show full text]
  • Zhuolin Jiang
    Zhuolin Jiang CONTACT 50 Moulton St, Cambridge, MA, 02138 Phone: +16178732017 INFORMATION Email: [email protected] Website: http://www.umiacs.umd.edu/~zhuolin/ RESEARCH Computer Vision: Object/Human Detection and Tracking, Object Categorization, Scene INTEREST Modeling and Recognition, Image Tagging/Annotation, Face Detection/Recognition/Verification, Action Detection/Recognition Machine Learning: Discriminative Feature Learning, Supervised Clustering, Submodular Op- timization and Matroid Theory, Sparse and Low-Rank Representation, Deep Learning, On- line/Incremental/Active Learning, Transfer Learning EMPLOYMENT Raytheon BBN Technologies, USA 04/2015 - Present Scientist II Noah’s Ark Research Lab, Huawei, Hong Kong 01/2013 - 03/2015 Researcher University of Maryland, College Park, USA 11/2011 - 12/2012 Assistant Research Scientist (a parallel rank at the Univ. of Maryland to Assistant Professor) University of Maryland, College Park, USA 06/2010 - 10/2011 PostdoctoralResearchAssociate Advisor:Prof.LarryS.Davis EDUCATION University of Maryland, College Park (UMD), USA 09/2008 - 05/2010 Exchange PhD student in Computer Science Advisor: Prof. Larry S. Davis South China University of Technology (SCUT), China 09/2004 - 06/2010 Ph.D. in Computer Science GPA: 3.51/4.0 Advisor: Prof. Shaofa Li Thesis: Research on Computer Vision-based Human Action Detection and Recognition China University of Petroleum (CUP), China 09/2000 - 06/2004 B.Eng. in Computer Science GPA: 3.53/4.0 Rank: 1/113 Advisor: Prof. Faming Gong Thesis: Research on Triangular Mesh Subdivision PUBLICATIONS (Number of Citations: 1790 based on Google Scholar) Jingjing Zheng, Zhuolin Jiang, Rama Chellappa. Submodular Attribute Selection for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (to appear), 2017.
    [Show full text]
  • AAAI-16 / IAAI-16 / EAAI-16 Program
    Thirtieth AAAI Conference on Artificial Intelligence Twenty-Eighth Conference on Innovative Applications of Artificial Intelligence The Sixth Symposium on Educational Advances in AI AAAI-16 / IAAI-16 / EAAI-16 Program February 12–17, 2016 Phoenix Convention Center / Hyatt Regency Phoenix Phoenix, Arizona, USA Sponsored by the Association for the Advancement of Artificial Intelligence Cosponsored by AI Journal, the National Science Foundation, Baidu, IBM Research, Infosys, Lionbridge, Microsoft Research, Disney Research, University of Southern California/Information Sciences Institute, Yahoo Labs!, ACM/SIGAI, CRA Computing Community Consortium (CCC), and David E. Smith MORNING AFTERNOON EVENING (AFTER 5:00 PM) Friday, February 12 Tutorial Forum Tutorial Forum Student Welcome Reception Workshops Workshops AAAI/SIGAI DC AAAI/SIGAI DC Saturday, February 13 Tutorial Forum Tutorial Forum Speed Dating Workshops Workshops Opening Reception AAAI/SIGAI DC AAAI/SIGAI DC EAAI EAAI Open House Invited Talks Open House Robotics Exhibits Robotics Exhibits Sunday, February 14 AAAI / IAAI Welcome / AAAI Awards Lunch with a Fellow Presidential Address: Dietterich IAAI Invited Talk: Rao AAAI Invited Talk: Krause AAAI / IAAI Technical Program AAAI / IAAI Technical Program AI Job Fair Classic Paper/Robotics Talks What’s Hot Talks / Robotics Talks Poster / Demo Session 1 EAAI EAAI Fellows Dinner Robotics/Vendor Exhibits Robotics/Vendor Exhibits Video Competition Viewing Video Competition Viewing Monday, February 15 Women’s Mentoring Breakfast AAAI Invited Talk:
    [Show full text]
  • 2020 AAAI Executive Council Candidate Statements
    2020 AAAI Executive Council Candidate Statements The AAAI Nominating Committee (consisting of Subbarao Kambhampati (Chair), Eugene Freuder, Claire Monteleoni, Cynthia Rudin, and Matthijs Spaan) has prepared a slate of two (2) candidates for the position of AAAI President-Elect and eight (8) candidates for Executive Councilor. The term of President-Elect is two years. The President-Elect automatically becomes President after the expiration of the current President's term. The President then holds the Past President position for the next two years. Councilors serve a three-year term of office. Please vote for no more than one (1) person for the position of President-Elect, and four (4) people for the position of Councilor. Write-in votes are allowed. Each candidate was asked "What is the most pressing issue facing AI and AAAI today?" Responses appear in the paragraphs labeled "Statement.” Please read this information before voting at the AAAI Membership URL sent to you via email. President-Elect Candidates (2) • Francesca Rossi • Qiang Yang Executive Councilor Candidates (8) • Edith Elkind • Susan L. Epstein • Christopher Geib • Laura Hiatt • Martin Michalowski • Barry O’Sullivan • Balaraman Ravindran • Kartik Talamadupula President-Elect Candidates (2) Francesca Rossi Francesca Rossi is an IBM fellow and the IBM AI Ethics Global Leader at the T.J. Watson IBM Research Lab. Before joining IBM, she was a professor of computer science at the University of Padova, Italy. Her AI research interests focus on preferences, multi-agent systems, computational social choice, constraint reasoning, fairness, and value alignment. Overall, she has published over 200 scientific articles on these topics.
    [Show full text]
  • 4Th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications
    Preface 4th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications http://bigdata-mining.org/ Recent years have witnessed a dramatic increase in our ability to collect data from various sensors, devices, in different formats, from independent or connected applications. This data flood has outpaced our capability to process, analyze, store and understand these datasets. Consider the Internet data. The web pages indexed by Google were around one million in 1998, but quickly reached 1 billion in 2000 and have already exceeded 1 trillion in 2008. This rapid expansion is accelerated by the dramatic increase in acceptance of social networking applications, such as Facebook, Twitter, Weibo, etc., that allow users to create contents freely and amplify the already huge Web volume. Furthermore, with mobile phones becoming the sensory gateway to get real-time data on people from different aspects, the vast amount of data that mobile carrier can potentially process to improve our daily life has significantly outpaced our past CDR (call data record)-based processing for billing purposes only. It can be foreseen that Internet of things (IoT) applications will raise the scale of data to an unprecedented level. People and devices (from home coffee machines to cars, to buses, railway stations and airports) are all loosely connected. Trillions of such connected components will generate a huge data ocean, and valuable information must be discovered from the data to help improve quality of life and make our world a better place. For example, after we get up every morning, in order to optimize our commute time to work and complete the optimization before we arrive at office, the system needs to process information from traffic, weather, construction, police activities to our calendar schedules, and perform deep optimization under the tight time constraints.
    [Show full text]
  • A Survey on Transfer Learning
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 22, NO. 10, OCTOBER 2010 1345 A Survey on Transfer Learning Sinno Jialin Pan and Qiang Yang, Fellow, IEEE Abstract—A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research. Index Terms—Transfer learning, survey, machine learning, data mining. Ç 1INTRODUCTION ATA mining and machine learning technologies have The need for transfer learning may arise when the data Dalready achieved significant success in many knowl- can be easily outdated. In this case, the labeled data edge engineering areas including classification, regression, obtained in one time period may not follow the same and clustering (e.g., [1], [2]).
    [Show full text]
  • Network on Network for Tabular Data Classification in Real-World Applications
    Network On Network for Tabular Data Classification in Real-world Applications Yuanfei Luo Hao Zhou Wei-Wei Tu [email protected] [email protected] [email protected] 4Paradigm Inc., Beijing, China 4Paradigm Inc., Beijing, China 4Paradigm Inc., Beijing, China Yuqiang Chen Wenyuan Dai Qiang Yang [email protected] [email protected] [email protected] 4Paradigm Inc., Beijing, China 4Paradigm Inc., Beijing, China Hong Kong University of Science and Technology, Hong Kong ABSTRACT ACM Reference Format: Tabular data is the most common data format adopted by our cus- Yuanfei Luo, Hao Zhou, Wei-Wei Tu, Yuqiang Chen, Wenyuan Dai, and Qiang tomers ranging from retail, finance to E-commerce, and tabular Yang. 2020. Network On Network for Tabular Data Classification in Real- world Applications. In Proceedings of the 43rd International ACM SIGIR data classification plays an essential role to their businesses. Inthis Conference on Research and Development in Information Retrieval (SIGIR ’20), paper, we present Network On Network (NON), a practical tabular July 25–30, 2020, Virtual Event, China. ACM, New York, NY, USA, 10 pages. data classification model based on deep neural network to provide https://doi.org/10.1145/3397271.3401437 accurate predictions. Various deep methods have been proposed and promising progress has been made. However, most of them use operations like neural network and factorization machines to fuse 1 INTRODUCTION the embeddings of different features directly, and linearly combine Tabular data is widely used in many real-world applications, such the outputs of those operations to get the final prediction. As a as online advertising [11, 33] recommendation [3], fraud detec- result, the intra-field information and the non-linear interactions tion [4, 32], medical treatment [18], which is also the scenario of between those operations (e.g.
    [Show full text]
  • Curriculum Vitae
    Yang Yang PhD in Computer Science Starting from Sept 2010 University of Maryland, College Park Bachelor of Science Graduate in June 2010 Computer Science and Applied Mathematics RM 518, Hall 6, Mobile: +852-66725956 The Hong Kong University E-mail: cs [email protected] of Science and Technology (HKUST) Website: http://bit.ly/bix8d4 Clear Water Bay, Kowloon Hong Kong Education History The Hong Kong University of Science and Technology 09/2006˜06/2010 University of Washington (Academic Exchange) 01/2009˜03/2009 Beijing No.4 High School 09/2003˜06/2006 Honors and Awards Outstanding Student, graduating class of 2010 The Joseph Lau Luen Hung Charitable Trust Scholarship, 2009˜ 2010 Silver Medal, International Genetically Engineered Machine Competition (iGEM), MIT Boston, 2009 Scholarship for Undergraduate Students with Outstanding Academic Performance, 2009˜ 2010 4th Place, ACM/ICPC Collegiate Programming Contest, Hong Kong, 2008 Dean’s List recipient 2007˜ 2009 School of Engineering Scholarship 2006˜ 2007 Second Prize, China Provincial Olympiad of Physics, Beijing, 2005 Research Experience Final Year Thesis (Honors Study Track), 09/2009˜ 04/2010, Supervisor: Gary Chan Topic: Cooperative Caching in Peer-to-Peer Video-on-Demand (P2PVoD) Achievement: Formulated Cooperative Caching problem and proved that it is NP-hard. Devised a distributed caching algorithm based on some heuristics. Undergraduate Research Opportunity Program (UROP), HKUST, Summer 2009, Supervisor: Qiang Yang Topic: Path Planning Using Markov Logic Network Model Achievement: Built a Lego NXT robot controller capable of path planning with the help of a Markov Logic Network model learned from historical data. UROP, HKUST, Summer 2008, Supervisor: Gary Chan Topic: P2P Live Streaming Achievement: Developed P2P live streaming network leveraging local IP-multicast capability.
    [Show full text]
  • Federated Machine Learning: Concept and Applications
    Federated Machine Learning: Concept and Applications QIANG YANG, Hong Kong University of Science and Technology, Hong Kong YANG LIU, Webank, China TIANJIAN CHEN, Webank, China YONGXIN TONG, Beihang University, China Today’s AI still faces two major challenges. One is that in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated learning framework, which includes horizontal federated learning, vertical federated learning and federated transfer learning. We provide definitions, architectures and applications for the federated learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allow knowledge to be shared without compromising user privacy. CCS Concepts: • Security and privacy; • Computing methodologies → Artificial intelligence; Machine learning; Supervised learning; Additional Key Words and Phrases: federated learning, GDPR, transfer learning ACM Reference Format: Qiang Yang, Yang Liu, Tianjian Chen, and Yongxin Tong. 2019. Federated Machine Learning: Concept and 12 Applications. ACM Trans. Intell. Syst. Technol. 10, 2, Article 12 (February 2019), 19 pages. https://doi.org/ 0000001.0000001 1 INTRODUCTION 2016 is the year when artificial intelligence (AI) came of age. With 59AlphaGo[ ] defeating the top human Go players, we have truly witnessed the huge potential in artificial intelligence (AI), and have began to expect more complex, cutting-edge AI technology in many applications, including driverless cars, medical care, finance, etc.
    [Show full text]
  • Curriculum Vitae Department of CSE, the Hong Kong University of Science and Technology Hong Kong SAR – China
    Yilun Jin | Curriculum Vitae Department of CSE, The Hong Kong University of Science and Technology Hong Kong SAR – China Æ +86-18101885710, +852-65837148 • Q [email protected] kl4805.github.io I am currently a PhD student from Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, advised by Prof. Qiang Yang and co-advised by Prof. Kai Chen. My current research interests lie in the field of Federated Learning, including algorithms and privacy & security. I am also interested in information network mining, including Graph Representation Learning, Graph Neural Networks, etc*. Education Ph.D. Student, Dept. of CSE, HKUST Hong Kong SAR + Computer Science and Engineering 9.2019– Advisor: Prof. Qiang Yang, Prof. Kai Chen (co-advisor). B. S. , School of EECS, Peking University Beijing, China + Computer Science, GPA: 3.7/4.0 9.2015–7.2019 Advisor: Prof. Guojie Song Selected courses: Advanced Algebra, Mathematical Analysis, Convex Optimization, Compiler Design. B. Economics, National School of Development, Peking University Beijing, China + Economics, GPA: 3.7/4.0 9.2016–7.2019 Selected courses: Intermediate Macro- & Micro-Economics, Econometrics, Financial Economics, Money and Banking, Special Topics on Reform in China University of California, San Diego La Jolla, USA + Exchange Student, GPA: 3.93/4.0 9.2017–12.2017 Courses: Computer Operating System, Machine Learning, Recommender System and Web Mining Experiences WeBank Shenzhen, China + Internship, advised by Dr. Lixin Fan 6.2020–12.2020 Research on federated learning, adversarial machine learning, and machine learning privacy. SenseTime Beijing, China + Research Internship on Video analysis 3.2018–6.2018 Implemented content-aware collaborative filtering based video recommendation algorithm, along with a dataset for video recommendation, consisting both video corpus and interaction data.
    [Show full text]
  • Conference Program
    CCF Conference No. CCF-18-TC18-01I The First CCF International Conference on Artificial Intelligence (CCF-ICAI 2018) Conference Program Host: China Computer Federation (CCF) Co-Host: CCF Technical Committee on Artificial Intelligence & Pattern Recognition Organizers: Shandong University, Shandong University of Finance and Economics, University of Jinan, Qilu University of Technology (Shandong Academy of Sciences), Shandong Electronic Chamber of Commerce Co-Organizers: Shandong Association of Artificial Intelligence, Yangzhou University Sponsors: 0 August 9-10,2018 Jinan, China 1 Contents I. Welcome to CCF-ICAI 2018 ................................................................................ 1 II. Organizing Committee ....................................................................................... 2 III. The 8th CCF Technical Committee on Artificial Intelligence & Pattern Recognition ................................................................................................................ 3 IV. Conference Schedule ......................................................................................... 8 1. List of Oral Session 1 ......................................................................................................................... 10 2. List of Oral Session 2 ......................................................................................................................... 10 V. Keynote Speakers .............................................................................................. 11 Ⅶ.
    [Show full text]