日本データベース学会の皆様、
NTT の新井です。
xSIG 2024 のポスター発表の募集についてお知らせいたします。
タイトル、著者情報、概要のみで手軽に発表を申し込むことができます。
締め切りまでの時間も 1 か月ほどありますので、システム系の取り組みを
されている方はぜひ発表をご検討ください。
(English follows Japanese)
xSIG 2024 Call for Posters
========================================
https://xsig.ipsj.or.jp/2024/
ポスター発表募集
--------------------
xSIG 2024では、全主催・協賛研究会の分野にまたがる幅広い分野 (cross-SIG) を対象としたポスター発表を募集します。
- 新たな研究の構想や問題提起、将来の展開を見据えた萌芽的な研究など、あらゆる段階の研究の紹介
- xSIG 2024およびSWoPP 2024の各研究会で口頭発表を行う研究の紹介
- 既発表の研究の紹介
- 研究・開発プロジェクトの紹介
学生を対象とした優秀ポスター発表の表彰を予定しています。
（ただし、xSIG 2024の口頭発表論文で受賞されている方は対象外とします）
学生、若手研究者に限らず、様々な年代の方の発表をお待ちしております。
xSIG 2024およびSWoPP
2024の各研究会で口頭発表を行う論文についても、ポスター発表することを推奨します。口頭発表の内容を踏まえて、ポスター発表を通じて密な議論がなされることを期待します。
ただし、ポスター発表の申込件数が多い場合には、より多くの方に発表機会を提供するために、xSIG 2024およびSWoPP
2024の各研究会で口頭発表を「行わないもの」を優先し、ポスター発表をお断りすることがございます。また、xSIGの関連分野外の発表についてもお断りすることがございます。予めご了承ください。
ポスターセッションはxSIG/SWoPP会場での「対面形式」での開催とします。
投稿
--------------------
投稿にはGoogle Forms（https://forms.gle/Nh1aDMS3U1TjhtLz8）を利用します。
投稿時に必要なものは、タイトル、著者情報、概要（和文200-400文字程度、英文100-200語程度）のみで、論文やExtended
Abstractは不要です。
xSIGウェブサイト上でタイトルと著者情報を掲載します。
発表
--------------------
xSIG 2024ポスターセッション（日時は後日告知）においてポスター発表を行ってください。
会場備付のボードにポスター（最大A0サイズを想定）を画鋲で貼り付けていただきます。
ポスター会場の様子については下のページもご参照ください。
https://www.google.co.jp/maps/@34.0752049,134.5461216,3a,75y,280.96h,79.81t…
電子版ポスターの提供は公式には行いませんが，希望者がSWoPPのSlack上にアップロードできる場を提供する予定です．
ポスター発表関連の日程
--------------------
- 投稿〆切: 2024年7月9日（火）23:59 (JST)
- 採否通知: 2024年7月10日（水）頃
- ポスターセッション: 2024年8月7日-9日（後日告知）
xSIG 2024 Call for Posters
========================================
https://xsig.ipsj.or.jp/2024/
Call for Posters
--------------------
xSIG 2024 solicits poster presentations from a wide range (cross-SIG)
fields of all sponsors and co-sponsors of xSIG.
- research of any stage, such as concept and problem presentation
- research presented at xSIG 2024 and SWoPP 2024 with an oral presentation.
- previously published research in other opportunities.
- introduction of research and development project.
We are planning to give poster awards for outstanding poster
presentations to students. (Please note that authors already awarded
for oral presentation papers of xSIG 2024 are ineligible for the
poster awards) We hope various researchers, not limited to students
and young researchers, have presentations here. xSIG 2024 encourages
authors of oral presentations of xSIG 2024 and SWoPP 2024 to introduce
their research again in the poster session for in-depth discussions.
If the number of submissions exceeds the available capacity, we might
decline some posters of oral presentation papers at xSIG and SWoPP in
order to provide presentation opportunities for more people. Also, we
might decline out-of-scope posters from the xSIG interests.
The poster session will be provided only on-site at the xSIG/SWoPP venue.
Submission
--------------------
You have to enter the author information, title, and abstract of your
poster. The abstract should be around 200-400 characters (in Japanese)
or 100-200 words (in English). The title and author(s) will be listed
on the xSIG website.
Submission System
--------------------
Poster submission page
https://forms.gle/Nh1aDMS3U1TjhtLz8
Poster Presentation
--------------------
Present your poster in the xSIG 2024 poster session.
You will need to attach your poster (maximum size A0) to the board
provided at the venue using thumbtacks.
Please also refer to the following page to see what the poster venue
will look like:
https://www.google.co.jp/maps/@34.0752049,134.5461216,3a,75y,280.96h,79.81t…
While we will not officially provide electronic versions of the
posters, we plan to offer a space on the SWoPP Slack where presenters
can upload their posters.
Poster schedule
--------------------
- Submission deadline: 23:59, July 9, 2024 (JST)
- Author notification: after July 10, 2024
- Poster session: August 7 - 9, 2024
--
新井 淳也 (ARAI Junya), PhD
Computer & Data Science Labs, NTT Corp.
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
