Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Federated Learning 連合学習
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
regonn
March 24, 2023
Technology
1.9k
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Federated Learning 連合学習
Regonn @関西Kaggler交流会 2023/03/24
regonn
March 24, 2023
More Decks by regonn
See All by regonn
Allora Network が実現する 「予測の経済圏」
regonn
0
39
Submission with Numerai Compute using GCP Batch
regonn
0
700
HelloMoon x Orca=HelloOrca
regonn
0
190
The Challenge of Automatically Configuring Numerai Compute Environment
regonn
0
150
PLATEAUをデータベースに取り込んでみた
regonn
0
1.8k
古参Numerai参加者の戯言
regonn
1
2.6k
Nim + Cloud Run + TerraformでGCPにNimのサーバーレス環境を作る
regonn
1
700
S+ Camera Basicと似た環境をラズパイから構築してみる
regonn
0
580
衛星画像のゴルフ場写り込み判定AIモデルを作る
regonn
0
920
Other Decks in Technology
See All in Technology
AIは爆速なのに、私が詰まっていた話 ― 音声入力と鳴くマスコットでボトルネックを削る
yama3133
0
530
自主式軟體工廠
philipz
0
230
「とりあえず動く」の先へ。 AI時代のチーム開発と内部設計/2026-slsdays
slsops
0
150
インバスケット試験対策アプリを 作って見えたAIエージェント構築 ナレッジ2選
shichijoyuhi
1
130
Meet AgentCore Identity Consent Portal
hironobuiga
3
190
AI 時代の Azure エンジニアリング ~ 私たちは何を磨き、何を任せるのか ~
chack411
1
520
BedrockとLambdaで作る リアルタイム進行型推理ゲーム
kawametho
0
190
[2026 Oracle Technical Deep Dive] AI時代のデータベース基盤をどう選ぶ? Exadata Database Serviceの選択肢と使い分け (2026年9月17日開催)
oracle4engineer
PRO
0
230
組み立てて楽しむ AWS Blocks 入門
kmiya84377
0
220
購入ドメインでの課題と取り組み
ykagano
0
150
今こそ知りたいAmplifyGen2
mkdev10
2
150
ミイダス株式会社 テックチームのご紹介 / MIIDAS Tech Team
miidas
0
160
Featured
See All Featured
Claude Code のすすめ
schroneko
67
230k
Groundhog Day: Seeking Process in Gaming for Health
codingconduct
0
390
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
920
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
3
270
WENDY [Excerpt]
tessaabrams
14
40k
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
2
460
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
11
1.1k
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
460
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
6.1k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.4k
The Illustrated Children's Guide to Kubernetes
chrisshort
51
53k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
570
Transcript
Regonn @ؔKagglerަྲྀձ 2023/03/24 Federated Learning ࿈߹ֶश
Regonn (@regonn_haizine) • Kaggle Competition Expert • Kaggle ؔ࿈ Podcast
(with ΧϨʔͪΌΜ) • ౡࠜͷϑϦʔϥϯε • ϒϩοΫνΣʔϯɾϝλόʔεɾػցֶश(Ӵσʔλɾ)ͷࣄҊ݅ • Solana Japan Orca(DEX: ࢄऔҾॴ) ͷ CM • ڈ͔Βۀ࢝Ίͯ·͢
࠷ۙ AI ͷਐา֮·͍͠ • ChatGPT-4 • Hugging Face ͷ͓͔͛Ͱɺత(Task)ʹ߹ͬͨɺֶशࡁΈϞσϧΛར༻͠ ͘͢ͳ͖͍ͬͯͯΔ
औಘ͕͍͠σʔλᶃ • ΤοδσόΠεσʔλ • ௨৴ଳҬͳͲͷ੍ݶ • શͯͷηϯαʔσʔλऔಘ͍͠
औಘ͕͍͠σʔλᶄ • ҩྍσʔλɾސ٬σʔλ • ϓϥΠόγʔ • ଞࣾؒͰͷڞ༗
Federated Learning(FL) ࢄͯ͠อ࣋͞ΕͨσʔλΛऩूɾू͢Δ͜ͱͳ͘ػցֶशϞσϧͷ܇࿅ʹ ༻͍Δํ๏
Federated Learning(FL)ͷछྨ • ਫฏ࿈߹ֶश • ਨ࿈߹ֶश • ࿈߹సҠֶश
ਫฏ࿈߹ֶश • ͦΕͧΕ͕ɺಉ͡ಛྔͰɺҟͳΔσʔληοτΛ͍࣋ͬͯͨ߹ • ΤοδσόΠεͰ͜ͷλΠϓ
ਫฏ࿈߹ֶश ᶃ ᶄ ᶅ ᶃϩʔΧϧͰֶश ᶄதԝαʔόʔʹଛࣦޯใΛૹΔ ᶅதԝαʔόʔͰΞϯαϯϒϧతॲཧ(ޯฏۉԽ) ᶆߋ৽͞ΕͨϞσϧΛશͯฦ͢ ᶆ
ਨ࿈߹ֶश • ͦΕͧΕಛྔҟͳΔ͕ɺಉ͡λʔήοτͷσʔλΠϯσοΫε͕ଘࡏ͢ Δ߹ ߴ ϩʔϯ ސ٬A xx yy ௨৴ྔ
՝ֹۚ ސ٬A xx yy ΫϨδοτΧʔυͷσϑΥϧτ༧ଌ σϑΥϧτ ސ٬A 1
ਨ࿈߹ֶश ߴ ϩʔϯ ސ٬A xx yy ސ٬C zz ww ௨৴ྔ
՝ֹۚ ސ٬A kk mm ސ٬B aa bb σϑΥϧτ ސ٬A 1 ސ٬D 0 ※ݫີͰͳ͍ தԝαʔόʔͰ҉߸伴Λ࡞Γެ։伴Λɺ ͦΕͧΕͷϩʔΧϧͰ҉߸Խ͠ɺ ΞϊχϚΠζ͞ΕͨσʔλͰֶश ߴ ϩʔϯ ௨৴ྔ աֹۚ σϑΥϧτ ސ٬A xx yy kk mm 1
࿈߹సҠֶश • ಛྔλʔήοτҟͳΔ߹ • ࣅ͍ͯΔυϝΠϯྖҬ • αΠζ͕େ෯ʹҟͳΔ߹
Federated Learningͷใु • ͦΕͧΕͷɺϞσϧߩݙʹԠͯ͡ใुΛܭࢉ͢ΔϩδοΫݚڀ͞Εͯ ͍Δ
Numerai • ۚ༥σʔλͷਨ࿈߹ֶशతͳͷ͕Ͱ͖͍ͯΔ • શੈքגࣜࢢͷגՁͷಈ͖ΛNumeraiଆ͕࡞ͨ͠Target 0~1Ͱ༧ଌ͢Δ • Numerai Signals ͰɺಛྔࣗͰ༻ҙͯ͘͠Δ
• ࣮ࡍʹσʔλͰϑΝϯυ͕ӡ༻͞ΕͯɺརӹͷҰ෦ΛϞσϧͷߩݙʹԠ͡ ͯ͞ΕΔ
Federated Learning ϥΠϒϥϦؔ࿈ • େ͖Ίͷͷͩͱ • https://github.com/tensorflow/federated • TensorflowFederated: Tensorflow
ͷެࣜ Federated ϥΠϒϥϦ • https://github.com/OpenMined/PySyft • PySyft: PyTorch Λ͏߹ͩͬͨΒɺͪ͜ΒΛ͏ • ͓ͦΒ͘ɺϥΠϒϥϦ͚ͩͰͳ͘αʔϏεࠓޙ૿͖͑ͯͦ͏
ࢀߟਤॻ Federated Learning: ϓϥΠόγʔอޢԼʹ͓͚Δػցֶश
ऴΘΓ