Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
論文紹介:Relaxed Softmax for PU Learning
Search
Hayato Maki
October 05, 2019
Research
3
950
論文紹介:Relaxed Softmax for PU Learning
論文リンク:
https://dl.acm.org/citation.cfm?id=3347034
Hayato Maki
October 05, 2019
Tweet
Share
More Decks by Hayato Maki
See All by Hayato Maki
Billion-scale Embedding for E-commerce Recommendation in Alibaba
hamaki
0
57
Today was a Good Day: The Daily Life of Software Developers
hamaki
0
58
MIRU 2019 Lunch on Seminar
hamaki
1
230
コーディネート整合性を考慮したカテゴリ間推薦
hamaki
0
1.2k
Regularization_The Element of Statical Learning
hamaki
0
150
Neural Activity During Sentence Processing as Reflected in Theta, Alpha, Beta, and Gamma Oscillations
hamaki
0
160
【ICML読み会】Unsupervised Deep Embedding for Clustering Analysis
hamaki
0
1.2k
Other Decks in Research
See All in Research
Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices
masakat0
0
220
LiDARとカメラのセンサーフュージョンによる点群からのノイズ除去
kentaitakura
0
130
機械学習でヒトの行動を変える
hiromu1996
1
310
第79回 産総研人工知能セミナー 発表資料
agiats
2
160
渋谷Well-beingアンケート調査結果
shibuyasmartcityassociation
0
260
Composed image retrieval for remote sensing
satai
1
100
Kaggle役立ちアイテム紹介(入門編)
k951286
14
4.6k
marukotenant01/tenant-20240826
marketing2024
0
510
Weekly AI Agents News!
masatoto
25
24k
MIRU2024_招待講演_RALF_in_CVPR2024
udonda
1
330
[CV勉強会@関東 CVPR2024] Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation / kantocv 61th CVPR 2024
shunk031
1
460
大規模言語モデルを用いた日本語視覚言語モデルの評価方法とベースラインモデルの提案 【MIRU 2024】
kentosasaki
2
520
Featured
See All Featured
The World Runs on Bad Software
bkeepers
PRO
65
11k
Speed Design
sergeychernyshev
25
620
Embracing the Ebb and Flow
colly
84
4.5k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
16
2.1k
Rails Girls Zürich Keynote
gr2m
94
13k
Docker and Python
trallard
40
3.1k
Producing Creativity
orderedlist
PRO
341
39k
A Philosophy of Restraint
colly
203
16k
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
Optimizing for Happiness
mojombo
376
70k
How to Ace a Technical Interview
jacobian
276
23k
Optimising Largest Contentful Paint
csswizardry
33
2.9k
Transcript
3FMBYFE4PGUNBYGPS 16-FBSOJOH 6HP5BOJFMJBOBOE'MBWJBO7BTJMF $SJUFP3FTFBSDI 3FD4ZT`จհBU8BOUFEMZΦϑΟε հऀɿਅ༐ਓBU;0;0ςΫϊϩδʔζ
3FMBYFE4PGUNBYGPS 16-FBSOJOH 6HP5BOJFMJBOBOE'MBWJBO7BTJMF $SJUFP3FTFBSDI 3FD4ZT`จհBU8BOUFEMZΦϑΟε 1PTJUJWFBOE6OMBCFMFE հऀɿਅ༐ਓBU;0;0ςΫϊϩδʔζ
1PTJUJWF6OMBCFMFE 16 -FBSOJOH 3 ਖ਼ྫʹ͚ͩϥϕϧ͕͍͍ͭͯΔ ϥϕϧ͕͍͍ͭͯͳ͍σʔλɺਖ਼ྫɾෛྫͲͪΒͷ Մೳੑ͋Γ ਪનɺݴޠϞσϧͷֶशͰΑ͋͘Δঢ়گ
ී௨ͷ̎Ϋϥεྨ 16-FBSOJOH ਖ਼ྫ ෛྫ ਖ਼ྫ ϥϕϧແ͠
$POUFYUVBM16-FBSOJOH 4 ʮϖΞʯʹͳΔͷΛ୳͢16-FBSOJOH ਖ਼ྫͷϖΞ͚͕ͩ༩͑ΒΕΔ ਖ਼ྫͱͯ͠༩͑ΒΕͳ͔ͬͨϖΞͷΫϥεෆ໌ ֶश࣌ B@ C@
B@ C@ B@O C@O B@ C@ B@ C@ ϖΞ̌ ϖΞ ϖΞO ਖ਼ྫ Ϋϥεෆ໌ ਪ࣌ ೖྗ ީิ܈ ʁ ʁ ʁ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ
ϑΝογϣϯʹ͓͚Δ$POUFYUVBM16-FBSOJOH 5 ͷΈ߹ΘͤΛϞσϧԽ͢Δ ਖ਼ྫϖΞίʔσΟωʔτڞ༗αΠτ͔ΒೖखՄೳ ෛྫϖΞཧܥͷେֶʹߦͬͯࣸਅΛࡱΔखʹೖΒͳ͍ ʹߘ͞Εͨ τοϓεͱϘτϜεͷϖΞ Έସ͑ͨϖΞ
ؔ࿈ݚڀ 6 ਖ਼ྫͷੜ͚ͩΛֶश͢Δ ҟৗݕͳͲͰΘΕ͍ͯΔΞϓϩʔν ϥϯΩϯάͷUPQ/͚ͩʹڵຯ͕͋Δਪનʹ͔ͳ͍ ೳಈֶश ஞ࣍తʹϥϕϧΛ͚͍ͭͯ͘
0SBDMF ਅͷϥϕϧΛ͚ΒΕΔԿ ͔ ͕ඞཁɺਓؒͷΞϊςʔλʔͳͲ ϥϕϧ͖ σʔλ Ϟσϧֶश ϥϕϧແ͠ σʔλ 0SBDMF ೖྗ ద༻ αϯϓϦϯά ϥϕϧ༩
ຊݚڀͷߩݙ 7 $POUFYUVBM16-FBSOJOHʹ͍ͭͯɺ ৽͍͠ଛࣦؔͱෛྫαϯϓϦϯάͷ ํ๏ΛఏҊ
͖݅ͷ࠷ਪఆ 8 w J͕༩͑ΒΕͨ࣌ͷKͷ͖݅ܦݧ ਖ਼ྫͷϖΞ ਖ਼ྫϖΞҎ֎ͷશͯͷΈ߹Θͤ w ෛͷର GVMMTPGUNBY w
ϖΞͷू߹ɿ w JͱKͷϕΫτϧදݱͷੵɿ
͖݅ͷ࠷ਪఆ 9 w J͕༩͑ΒΕͨ࣌ͷKͷ͖݅ܦݧ ਖ਼ྫͷϖΞ ਖ਼ྫϖΞҎ֎ͷશͯͷΈ߹Θͤ w ෛͷର GVMMTPGUNBY
ͲͷJʹରͯ͠ ֤Kಉ͡ස ֬ Ͱෛྫͱͯ͠αϯϓϧ ͞ΕΔ ਅͷ͖݅ʹ JJEΛԾఆ w ϖΞͷू߹ɿ w JͱKͷϕΫτϧදݱͷੵɿ
ఏҊ
3FMBYFE4PGUNBY 34 -PTT 11 ෛྫαϯϓϦϯάɹɹʹ͍ͭͯɺଛࣦΛҎԼͷࣜͰఆٛ 'VMMTPGUNBY '4 ͱͷൺֱ
3FMBYFE4PGUNBY 34 -PTT 12 ෛྫαϯϓϦϯάɹɹʹ͍ͭͯɺଛࣦΛҎԼͷࣜͰఆٛ 'VMMTPGUNBY '4 ͱͷൺֱ
ͯ͢ͷKʹ͍ͭͯܭࢉ 2@J͕Ұ༷ͳΒɺ34'4ͷϞϯςΧϧϩۙࣅ 2@JͰαϯϓϧ͞ΕͨKͷू߹ 7 J K ʹ͍ͭͯܭࢉ
ੵΛߟྀͨ͠ෛྫαϯϓϦϯά 13 3FMBYFETPGUNBYΛඍ /VNCFSPGOFHBUJWFTBNQMFTˠ♾ ੵͷFYQΛ2@JͰॏΈ͚ ͨ͠ϘϧπϚϯ
ϘϧπϚϯෛྫαϯϓϦϯά 14 ෛྫʹͳΓ͢͞ʢOFHBUJWJUZʣͷࣄલࣝΛදݱ 5Λௐ͢Δ͜ͱͰෛྫαϯϓϦϯάͷੑ࣭Λௐ͢Δ ɿEFHFSBDZEJTUSJCVUJPO ॖୀ 5ɿԹύϥϝʔλ
ෛྫαϯϓϦϯάʹ͓͚ΔτϨʔυΦϑ 15 wϞσϧ͕ޡྨ͍͢͠ෛྫΛαϯϓϦϯά͍ͨ͠ ޡྨ͍͢͠ਖ਼ྫͱͷੵ͕େ͖͍ʢྨࣅ͕େ͖͍ʣ ຊਖ਼ྫͷσʔλΛɺෛྫͱͯ͠αϯϓϧͯ͠͠·͏ةݥ͕େ͖͍ wຊਖ਼ྫͷσʔλΛෛྫͱͯ͠αϯϓϦϯάͨ͘͠ͳ͍ ਖ਼ྫͱͷੵ͕খ͍͞ʢྨࣅ͕খ͍͞ʣσʔλΛαϯϓϦϯά
Ϟσϧʹͱͬͯ༰қʹࣝผՄೳɻใྔ͕গͳ͍ ϘϧπϚϯͷԹύϥϝλͰௐ
Թύϥϝλ 16 5ˠͷ࣌ɺਖ਼ྫͱͷੵ͕େ͖͍σʔλΛத৺ʹ୳ࡧ 5ˠ♾ͷ࣌ɺਖ਼ྫͱͷੵ͕খ͍͞σʔλΛத৺ʹ୳ࡧ 5 5 5
࣮ݧ
࣮ݧɿਓσʔλ ࠞ߹ਖ਼ن1@JͰσʔλΛੜ ਅͷͱਪఆ͞Εͨͷ,-μΠόʔδΣϯεͰධՁ ෛྫͷαϯϓϦϯάʹઃఆ ϘϧπϚϯͷઃఆ ܇࿅
ςετ ܇࿅ ςετ ܇࿅σʔλສɺόοναΠζΛมԽ όοναΠζɺ܇࿅σʔλΛมԽ 18
αϯϓϦϯά ଛࣦ .-& 'VMM 4PGUNBY 44 1PQVMBSJUZ 4PGUNBY 64 6OJGPSN
3FMBYFE4PGUNBY 6#4 #PUM[NBOO VOJGPSN 3FMBYFE4PGUNBY 14 1PQVMBSJUZ 3FMBYFE4PGUNBY 1#4 #PUM[NBOO QPQVMBSJUZ 3FMBYFE4PGUNBY #PUM[NBOOαϯϓϦϯάͷ༗ޮੑ͕֬ೝͰ͖Δ ࣮ݧɿਓσʔλ 19 όοναΠζ
࣮ݧɿ/FYUJUFN1SFEJDUJPO w .PWJFMFOT ສϨίʔυ w /FUqJYʢສϨίʔυʣ w 8JLJQFEJB5FYU ࠷ϙϐϡϥʔͳສ୯ޠ
w ̏୯ޠҎʹొͨ͠ΒϙδςΟϒͱΈͳ͢ 20 σʔλ ධՁࢦඪ w w .13 .FBO1FSDFOUJMF3BOL w 1SFDJTJPOBU
݁Ռɿ/FYUJUFN1SFEJDUJPO 21 αϯϓϦϯά ଛࣦ .-& 'VMM 4PGUNBY 44 1PQVMBSJUZ 4PGUNBY
64 6OJGPSN 3FMBYFE4PGUNBY 6#4 #PUM[NBOO VOJGPSN 3FMBYFE4PGUNBY 14 1PQVMBSJUZ 3FMBYFE4PGUNBY 1#4 #PUM[NBOO QPQVMBSJUZ 3FMBYFE4PGUNBY
·ͱΊ 22 $POUFYUVBM16-FBSOJOHʹ͍ͭͯɺ3FMBYFE4PGUNBYଛࣦͱ ϘϧπϚϯෛྫαϯϓϦϯάΛఏҊ ਓσʔλɺ/FYUJUFNQSFEJDUJPOͰ༗ޮੑΛ֬ೝ Թύϥϝʔλͷಈతௐ
$//ɺ3//ͳͲʹର͢ΔదԠ ܭࢉྔ͕ଟͦ͏ʁ จλΠτϧͷ͚͔͕͍ͭͨͬͨͳ͍ 'VUVSF8PSL ॴײ