Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Collaborative Topic Modeling for Recommending Scientific Articles

8a7e83d2e447783ab6d824f553429a09?s=47 Shinichi Takayanagi
May 30, 2016
Research
0
1.1k

Collaborative Topic Modeling for Recommending Scientific Articles

論文"Collaborative Topic Modeling for Recommending Scientific Articles"を読んだ際に使用したスライド

8a7e83d2e447783ab6d824f553429a09?s=128

Shinichi Takayanagi

May 30, 2016
Tweet

More Decks by Shinichi Takayanagi

See All by Shinichi Takayanagi
[KDD2021 論文読み会] ControlBurn: Feature Selection by Sparse Forests
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
2
1.4k
[ICML2021 論文読み会] Mandoline: Model Evaluation under Distribution Shift
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
0
1.6k
[情報検索/推薦 各社合同 論文読み祭 #1] KDD ‘20 "Embedding-based Retrieval in Facebook Search"
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
2
400
【2020年新人研修資料】ナウでヤングなPython開発入門
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
29
17k
論文読んだ「Simple and Deterministic Matrix Sketching」
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
1
610
Quick Introduction to Approximate Bayesian Computation (ABC) with R"
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
3
220
The Road to Machine Learning Engineer from Data Scientist
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
5
3.3k
論文読んだ「Winner’s Curse: Bias Estimation for Total Effects of Features in Online Controlled Experiments 」
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
1
3.6k
論文読んだ「Class Imbalance, Redux」
8a7e83d2e447783ab6d824f553429a09?s=48 stakaya
4
2.6k

Other Decks in Research

See All in Research
パーツ探し
Be0f86176276318b4b9775d795278f7e?s=48 yushiku
PRO
1
490
Offline Time-Independent Multi-Agent Path Planning
8462b18bc6d57cac5579ef4b2f64a6de?s=48 kei18
0
120
汎用音響信号表現の発展について@TokyoBISHBash#07
24ffdd65229aac1e9e6d65fe208a33a9?s=48 daisukelab_cs
0
230
論文紹介 / GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation
2ad725754b7ea0ff9e0abb9b7017fc07?s=48 forest1988
1
130
アノテーションのバイアス排除に関する2020年代の研究動向
Cb3c74960f845f8309702eb95f7e2f2a?s=48 kuri8ive
1
490
蓄電池経済効果シミュレーションを提示するとお客さんは販売会社を信頼するか？購入意欲はアップするか？最新調査結果
109732ee6f79ce8bd76989c7a7a88c45?s=48 satoru_higuchi
0
1.9k
Navigation for a team of agents
8462b18bc6d57cac5579ef4b2f64a6de?s=48 kei18
0
370
企業の女性活躍推進 分析レポート2022年版 -Forbes JAPAN WOMEN AWARD
02577d598059f231a2770ab944e71470?s=48 libinc
1
180
Fairseq初心者向けチュートリアル
58435510ebd76669ad6106bcf93d9afb?s=48 tktkbohshi
2
1.1k
Structure of NLP Papers
1ce0216a2274827385dab9a066077d98?s=48 ukyh
2
130
P値のトリセツ
4fe5193960c3289769e3913281560dc4?s=48 taka88
10
5.3k
AI最新論文読み会2022年6月
874ff503a00697a857e198a0ebb8f55f?s=48 ailaboocu
0
260

Featured

See All Featured
JazzCon 2018 Closing Keynote - Leadership for the Reluctant Leader
3ab1249be442027903e1180025340b3f?s=48 reverentgeek
173
8.6k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
B3ace07412a5178ea778e7eec161fc0a?s=48 jcasabona
12
940
Unsuck your backbone
B83d5b590577969ee79a5ad845411a7d?s=48 ammeep
659
55k
Statistics for Hackers
56c4053438af8e8b90d6f53cbb7573be?s=48 jakevdp
782
210k
Dealing with People You Can't Stand - Big Design 2015
44b54d2ffcb7857004071cc6795dde11?s=48 cassininazir
351
21k
Ruby is Unlike a Banana
6804f1775cb4babfcc3851298566fbce?s=48 tanoku
91
9.3k
Code Reviewing Like a Champion
C7393b7ba7ec9c8890dd77d209fbb3c9?s=48 maltzj
506
37k
Put a Button on it: Removing Barriers to Going Fast.
Bfd6b681ec6e8c9bef82ff0521c364f7?s=48 kastner
56
2.3k
It's Worth the Effort
Ba530e786553390f3fb271848485681c?s=48 3n
172
26k
YesSQL, Process and Tooling at Scale
D09fad3e36ae6841f54820be0e907f7a?s=48 rocio
157
12k
Designing for Performance
245cee81a9c424266e5e401d844ea881?s=48 lara
597
64k
Debugging Ruby Performance
D47656e20ff5e42f125fc5ea0fd636c6?s=48 tmm1
65
10k

Transcript

  1. RCO論文輪読会(2016/05/27) “Collaborative topic modeling for recommending scientific articles”(KDD2011) Chong Wang,

    David M. Blei 高柳慎一

  2. （C）Recruit Communications Co., Ltd. ABSTRACT 1

  3. （C）Recruit Communications Co., Ltd. 1. INTRODUCTION 2

  4. （C）Recruit Communications Co., Ltd. 1. INTRODUCTION 3

  5. （C）Recruit Communications Co., Ltd. 1. INTRODUCTION 4

  6. （C）Recruit Communications Co., Ltd. 2. BACKGROUND ＆ 2.1 Recommendation Tasks

    5

  7. （C）Recruit Communications Co., Ltd. 2.1 Recommendation Tasks 6

  8. （C）Recruit Communications Co., Ltd. 2.1 Recommendation Tasks 7

  9. （C）Recruit Communications Co., Ltd. 2.2 Recommendation by Matrix Factorization 8

  10. （C）Recruit Communications Co., Ltd. 2.2 Recommendation by Matrix Factorization 9

  11. （C）Recruit Communications Co., Ltd. 2.2 Recommendation by Matrix Factorization 10

  12. （C）Recruit Communications Co., Ltd. 2.2 Recommendation by Matrix Factorization 11

  13. （C）Recruit Communications Co., Ltd. 2.3 Probabilistic Topic Models 12

  14. （C）Recruit Communications Co., Ltd. LDAの生成過程 13

  15. （C）Recruit Communications Co., Ltd. LDAの特徴 14

  16. （C）Recruit Communications Co., Ltd. 3. COLLABORATIVE TOPIC REGRESSION 15

  17. （C）Recruit Communications Co., Ltd. COLLABORATIVE TOPIC REGRESSION 16

  18. （C）Recruit Communications Co., Ltd. CTRの生成過程 17

  19. （C）Recruit Communications Co., Ltd. 3. COLLABORATIVE TOPIC REGRESSION 18

  20. （C）Recruit Communications Co., Ltd. CTRのモデルのRegressionたる所以 19

  21. （C）Recruit Communications Co., Ltd. 学習のさせ方 20

  22. （C）Recruit Communications Co., Ltd. 学習のさせ方 21

  23. （C）Recruit Communications Co., Ltd. 簡単な証明 by iPad手書き 22

  24. （C）Recruit Communications Co., Ltd. 学習のさせ方 23

  25. （C）Recruit Communications Co., Ltd. 予測 24

  26. （C）Recruit Communications Co., Ltd. 4. EMPIRICAL STUDY 25

  27. （C）Recruit Communications Co., Ltd. データの規模感 26

  28. （C）Recruit Communications Co., Ltd. 評価 27

  29. （C）Recruit Communications Co., Ltd. 結果 28

  30. （C）Recruit Communications Co., Ltd. 結果 (ライブラリ内の論文数(Fig 5)・ある論文をLikeした数(Fig 6) 依存性) 29

    数が増えると Recallが下がる (あまり有名な論文じゃ ないのを出すため) 数が増えると Recallが上がる (みんな見てる論文 だとCFがうまく動く)

  31. （C）Recruit Communications Co., Ltd. 結果(ある2ユーザの好んだトピックを抽出) 30 トピックの潜 在ベクトルの 重みをランキ ングして抽出

  32. （C）Recruit Communications Co., Ltd. 結果(オフセットの大きかった論文BEST 10) 31 ※内容よりもCFが効くケースに相当

  33. （C）Recruit Communications Co., Ltd. 結果(EMの論文がベイズ統計勢にもよく参照されている例) 32 ※内容よりもCFが効く ケースに相当

  34. （C）Recruit Communications Co., Ltd. 結果(逆にトピックが広がらない例) 33 ※内容が支配的なケー スに相当

  35. （C）Recruit Communications Co., Ltd. 5. CONCLUSIONS AND FUTURE WORK 34