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