日本データベース学会の皆様
いつもお世話になっております。東工大の曹と申します。
来週の木曜日(6月6日)に、サイモンフレーザー大学(SFU)のケイ・ワン(Ke Wang)教授による東工大で講演が行われます。
ケイ・ワン教授はデータマイニング分野の著名な研究者で、特にプライバシーを保護するデータマイニングに関する専門書で知られています。
今回の東京工業大学での講演テーマはフェデレーテッドラーニングに関連しています。
Zoomと東工大の現地会場でハイブリッド形式で開催しますので、皆様ぜひ積極的にご参加ください。
Prof. Ke Wang from Simon Fraser University (SFU) will give a lecture next
Thursday (June 6, 13:00-14:00).
Prof. Ke Wang is a well-known researcher in the field of data mining and is
renowned for his technical book on privacy-preserving data publishing. The
topic of his talk at Tokyo Tech is related to Federated Learning.
The talk will be given hybrid via Zoom and on-site, so everyone is
encouraged to attend.
*日時:* *2024/6/6 13:00-14:00 *
*ZOOM: https://zoom.us/j/94209664502
<https://zoom.us/j/94209664502> (maximum 300 participants)*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Talk Title: *
Differentially Private Machine Learning for Decentralized and Time-evolving
Data
*Abstract:*
Decentralized machine learning focuses on learning from data distributed at
multiple related sites, where due to privacy or regulatory concerns, data
pooling is not an option.
In contrast to the real-world requirements, current methods in
decentralized machine learning, notably federated learning, force
participating sites into tight collaboration where the sites are forced
into symmetric sharing and shared decision making. That is, all sites have
to contribute their data to benefit from the learning process, and have to
share the same model types, architectures, training methodologies, feature
and sample spaces, etc. The issues are compounded in the case of
privacy-preservation and time-evolving data streams, where the sites have
to agree on a common, one-size-fits-all privacy budget, and the continuous
model updates required for handling time-evolving data streams erode the
privacy budget, deteriorating utility. Forced tight collaboration creates
barriers to participation where participating sites want to benefit from
other sites’ data but do not wish to share their own information or change
the existing data analysis practices.
In this work, we propose an end-to-end solution for differentially private
decentralized learning. Where our first contribution is PubSub-ML, a
differentially private, decentralized learning framework under loose
collaboration for static data. Proposed as an alternative to federated
learning, PubSub-ML allows the participating sites to maintain autonomy on
all decisions related to their learning processes. Our second contribution
is DP-Ensemble, a differentially private, dynamic model integration
approach for a single site that allows unlimited model updates for
time-evolving data streams on a fixed privacy budget. Our third
contribution extends PubSub-ML to data streams using DP-Ensemble, allowing
differentially private, decentralized modeling of data streams under loose
collaboration and a fixed privacy budget. All contributions are supported
by extensive empirical evaluation.
*Speaker*: Professor Ke Wang, Simon Fraser University
*Bio*:
Professor Ke Wang received Ph.D from Georgia Institute of Technology. He is
currently a professor at School of Computing Science, Simon Fraser
University. Ke Wang's research interests include database technology, data
mining and knowledge discovery, with emphasis on massive datasets, graph
and network data, and data privacy. He co-authored a book "Introduction to
Privacy-Preserving Data Publishing: Concepts and Techniques", Data Mining
and Knowledge Discovery Series, Chapman & Hall/CRC, August 2010.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
どうぞよろしくお願いいたします。
曹 洋
日本データべース学会の皆様:
早稲田大学の山名(General co-Chairs)です。
日本で初めての開催となる第10回IEEE International Conference on Smart Computing(大阪, 6/29-7/2)の参加登録(早期)の締切は、5月31日(AoE)となっております。ぜひ、多くの皆様にご参加いただけますと幸いです。
SmartComp2024
https://smartcomp.w.waseda.jp/
スマートコンピューティングは、センサーベース技術、モノのインターネット、 サイバーフィジカルシステム、エッジコンピューティング、ビッグデータ分析、機械学習、コグニティブコンピューティング、人工知能の複数の専門分野にわたる学際的な研究領域です。 スマートコンピューティングの応用は、交通、エネルギー、環境保護、スマート・コネクテッド・コミュニティ、ヘルスケア、バンキング、産業システム、エンターテインメント、ソーシャルメディア等、 さまざまな社会領域を含んでいます。
以下に会議のハイライトを示します:
--
<Registration Information>
Our SmartComp2024's early bird registration ends on May 31st (AoE). We appreciate your registration for SmartComp2024 by May 31st.
https://smartcomp.w.waseda.jp/registration/
<Information of SmartComp2024>
We have 26 main track papers, 4 posters, 3 demos, and 8 PhD Forum with 5 workshops.
You can find out tentative schedule from <https://smartcomp.w.waseda.jp/schedule/> https://smartcomp.w.waseda.jp/schedule/
The followings are highlights of SmartComp 2024.
<Keynotes>
June 30th 8:45-9:45
Prof. Paul Lukowicz (DKFI and University of Kaiserslautern, Germany)
July 1st 8:45-9:45
Prof. Niki Trigoni (University of Oxford, UK)
(Additional keynote to be announced soon)
<Panel>
2nd June, 8:45-10:15
Generative, Creative, Cooperative ? The transformative element of AI for Smart Computing
Panelists:
Takashi Takenaka (NEC)
Qi Han (Colorado School of Mines)
Sozo Inoue (Kyushu Institute of Technology)
Nalini Venkatasubramanian (University of California, Irvine)
(Additional panelists to be announced soon)
<Tutorials>
29th June, 14:45-16:45
1) The Internet of Bio-Nano Things -Smart Computing in the Human Body
Prof. Stefan Fischer, the University of Lubeck, Germany
2) Contactless Physiological Health Sensing: Challenges, Solutions & Opportunities
Prof. Nirmalya Roy, University of Maryland Baltimore County, USA
Ph.D. candidate Zahid Hasan, University of Maryland Baltimore County, USA
1st July, 13:15-15:15
1) Advancing Smart Computing: A Comprehensive Tutorial to 3D Point Clouds
Asst. Prof. Tatsuya Amano, Osaka University, JAPAN
Assoc. Prof. Hamada Rizk, Osaka University, JAPAN and Tanta University, Egypt
2) Science of Cyber Physical Security in Smart Living Applications
Prof. Sajal K. Das, Missouri University of Science and Technology, USA
Asst. Prof. Shameek Bhattacharjee, Western Michigan University, USA
--
<Reception> (17:45-20:00 of June 29th) (The maximum number of participants is limited)
Osaka Yakatabune (Japanese Style Boat Cruise)
<Banquet> (18:30-21:00 of July 1st)
Venue : the Landmark Square Osaka
https://www.landmark-osaka.com.e.ahs.hp.transer.com/
--
DBSJメーリングリストの皆様、
東京大学の山肩です。
2025年1月8(VBSは7)~10日に奈良で開催される
マルチメディアに関する国際学会 MMM 2025 のご案内です。
RegularとSpecial Session論文 投稿締切:
2024年7月22日(月)
皆様のご発表申し込みをお待ちしております。
==================================================================
The 31th International Conference on MultiMedia Modeling — MMM 2025
January (VBS: 7-) 8 – 10, 2025 in Nara, Japan
https://mmm2025.net/
==================================================================
Fist Call for Paper for MMM2025
MMM is a leading international conference for researchers and industry
practitioners for sharing new ideas,
original research results and practical development experiences from
all MMM related areas.
The conference calls for research papers reporting original
investigation results and demonstrations reporting
novel and compelling applications. Special sessions, keynote lectures,
the Video Browser Showdown will also
contribute to a high-quality program.
Details and updates will be published on the conference’s Web site:
https://mmm2025.net/
Call for Contributions
MMM 2025 solicits submissions of contributions for the following programs:
* Full papers
* Special Sessions
* Demo Sessions
* Video Browser Showdown (VBS on 7th Jan.)
MMM 2025 proposes five special sessions:
* SpIMA: Spatial Intelligence in Multimedia Analytics
* Multimedia Research in Robotics
* MLLMA: Multimodal Large Language Models and Applications
* ExpertSUM: Expert-Level Text Summarization from Fine-Grained
Multimedia Analytics
* Simulating Edge Computing and Multimodal AI: A Benchmark for
Real-World Applications
Important Dates:
* Regular and Special Session Paper Submission: July 22, 2024
* Demo Paper Submission: 19 August, 2024
* Video Browser Showdown Submission: 6 September, 2024
* Regular and Special Session Paper Notification: September 24, 2024
* Camera Ready Version and Registration: October 23, 2024
All paper submissions must conform to the formatting instructions of
Springer Verlag, LNCS series,
and must strictly adhere to the submission schedule.
MMM seeks contributions on the following research topics:
Multimedia Content Analysis
* Multimedia indexing
* Multimedia mining
* Multimedia abstraction and summarisation
* Multimedia annotation, tagging and recommendation
* Multimodal analysis for retrieval applications
* Semantic analysis of multimedia and contextual data
* Interactive learning
* Multimedia knowledge acquisition and construction
* Multimedia verification
* Multimedia fusion methods
* Multimedia content generation
Multimedia Signal Processing and Communications
* Media representation and algorithms
* Multimedia sensors and interaction modes
* Multimedia privacy, security and content protection
* Multimedia standards and related issues
* Multimedia databases, query processing, and scalability
* Multimedia content delivery, transport and streaming
* Wireless and mobile multimedia networking
* Sensor networks (video surveillance, distributed systems)
* Audio, image, video processing, coding and compression
* Multi-camera and multi-view systems
Multimedia Applications, Interfaces and Services
* Media content retrieval, browsing and recommendation tools
* Extended reality (AR/VR/MR) and virtual environments
* Real-time and interactive multimedia applications
* Multimedia analytics applications
* Egocentric, wearable and personal multimedia
* Urban and satellite multimedia
* Mobile multimedia applications
* Question answering, multimodal conversational AI and hybrid intelligence
* Multimedia authoring and personalisation
* Cultural, educational and social multimedia applications
* Multimedia for e-health and medical applications
Ethical, Legal and Societal Aspects of Multimedia
* Fairness, accountability, transparency and ethics in multimedia modeling
* Environmental footprint of multimedia modeling
* Large multimedia models and LLMs
* Multimodal pretraining and representation learning
* Reproducibility, interpretability, explainability and robustness
* Embodied multimodal applications and tasks
* Responsible multimedia modeling and learning
* Legal and ethical aspects of multimodal generative AI
* Multimedia research valorisation
* Digital transformation