【論文紹介】ImRec: Learning Reciprocal Preferences Using Images / recsys2020-imrec

3c0649db1ae5ca0ae57c76037243f501?s=47 Yuya Matsumura
October 17, 2020

【論文紹介】ImRec: Learning Reciprocal Preferences Using Images / recsys2020-imrec

2020年10月17日 RecSys2020論文読み会(オンライン) (https://connpass.com/event/189192/) における発表資料です。

以下の論文について概要を紹介しました。

- J Neve, R McConville.2020. Proceedings of the 14th ACM Conference on Recommender Systems, 170-179.
- https://dl.acm.org/doi/10.1145/3383313.3411476

最近盛り上がってきている相互推薦システム(Reciprocal Recommender Systems)についての論文で、オンラインデーティングサービスにおけるユーザのプロフィール画像を用いた内容ベースのアルゴリズム ImRec の提案がなされています。

3c0649db1ae5ca0ae57c76037243f501?s=128

Yuya Matsumura

October 17, 2020
Tweet

Transcript

  1. Yuya Matsumura @yu-ya4 ʲ࿦จ঺հʳ ImRec: Learning Reciprocal Preferences Using Images

    RecSys2020 ࿦จಡΈձʢΦϯϥΠϯʣ 17 Oct. 2020 J Neve, R McConville.2020. Proceedings of the 14th ACM Conference on Recommender Systems, 170-179. Photo by Agustín Diaz on Unsplash
  2. ✓ দଜ ༏໵ʢYuya Matsumuraʣ ✓ ژ౎େֶେֶӃ৘ใֶݚڀՊ म࢜՝ఔमྃʢాதݚڀࣨ -> ٢઒ݚڀࣨʣ ✓

    Wantedly, Inc. Matching Squad / Visit Data Chapter ✓ νʔϜϦʔυɺσʔλαΠΤϯεɺϓϩμΫτϚωδϝϯτ ✓ Wantedly Visit ʹ͓͚ΔσʔλΛ׆༻ͨ͠ϓϩμΫτʢਪનγεςϜʣͷ։ൃ @yu-ya4 @yu__ya4 ࣗݾ঺հ
  3. ૬ޓਪનγεςϜʢReciprocal Recommender Systemsʣͱ͸ʁ

  4. ʮαʔϏε಺ͷϢʔβΛޓ͍ʹਪન͢ΔγεςϜʯ User Item ैདྷͷҰൠతͳਪનγεςϜ ૬ޓਪનγεςϜ User(Female) User(Male) User(Job Seeker) User(Recruiter/Company)

    ex. Amazon, Netflix ex. Tinder, Pairs ex. Wantedly, LinkedIn ૬ޓਪનγεςϜʢReciprocal Recommender Systemsʣͱ͸ʁ
  5. 1. ਪનͷ"੒ޭ" • ਪનΛड͚ΔϢʔβ (subject) ͱਪન͞ΕΔϢʔβ (object) ͷ྆ํͷᅂ޷͕Ұகͯ͠ॳΊͯਪન͕"੒ޭ" 2. ਪનγεςϜʹର͢ΔϢʔβͷೝࣝ

    • subject Ϣʔβࣗ਎͕ "૬ޓਪનγεςϜ"Ͱ͋Δ͜ͱΛೝ্ࣝͨ͠Ͱɺobject Ϣʔβͷᅂ޷Λߟ্ྀͨ͠Ͱߦಈ 3. Ϣʔβ͔Β໌ࣔతʹఏڙ͞ΕΔϓϩϑΟʔϧ΍ᅂ޷ʹ͍ͭͯͷ৘ใ • Ϣʔβ͕ࣗ਎Ͱఏڙ͢Δ໌ࣔతͳϓϩϑΟʔϧ΍ᅂ޷৘ใ͕๛෋͕ͩɺͦΕΒ͕ඞͣ͠΋ਖ਼͘͠ͳ͍ 4. ϢʔβͷϥΠϑαΠΫϧ • ϢʔβͷϥΠϑαΠΫϧ͕୹͘ɺϢʔβͷߦಈʹجͮ͘҉໧తͳϢʔβͷᅂ޷৘ใ͕ू·Γʹ͍͘ 5. ϢʔβͷγεςϜ಺ʹ͓͚Δߦಈͷ࢟੎ • ೳಈతͳϢʔβͱडಈతͳϢʔβ͕ଘࡏ͠ɺडಈతͳϢʔβ͸ਪન͞Εͳ͍ͱ੒ޭମݧΛಘ೉͍ ૬ޓਪનγεςϜͷಛ௃΍՝୊
  6. ૬ޓਪનγεςϜͷʢయܕతͳʣ࢓૊Έ Aggregation Function User A to User B Preference Score

    User B User A User B to User A Preference Score User B User A Reciprocal Preference Score User B User A Arithmetic Mean, Harmonic Mean, or ...
  7. ؔ࿈ݚڀ/طଘख๏ 1/2 • [RECON] (Pizzato 2010) RECON: A Reciprocal Recommender

    for Online Dating • աڈʹ޷ҙΛࣔͨ͠૬खϢʔβͷ໌ࣔతͳϓϩϑΟʔϧʹڞ௨͢Δཁૉ͔ΒɼϢʔβ͝ͱͷ҉໧తͳᅂ޷৘ใʢetc. ମܕɼੑ ֨ɼֶྺ…ʣΛநग़ • ᅂ޷৘ใͱ૬खϢʔβͷ໌ࣔతͳϓϩϑΟʔϧͷҰக౓Λܭࢉ͢ΔίϯςϯπϕʔεͳΞϓϩʔνʹΑΓ୯ํ޲ͷద߹౓Λද ͢ Preference Score Λࢉग़ • ̎ͭͷ Preference Score ͔ΒAggregation Functionʢௐ࿨ฏۉʣͰ૒ํ޲ͷద߹౓Λද͢ Reciprocal Preference Score Λࢉग़ • [RCF] (Xia 2015) Reciprocal Recommendation System for Online Dating • ߦಈཤྺʢLike or Nopeʣʹجͮ͘ϢʔβϕʔεͷڠௐϑΟϧλϦϯάʢk-ۙ๣ʣͰ Preference Score Λࢉग़ • Aggregation Function ͸ௐ࿨ฏۉΛར༻ • RECON (Pizzato 2010) ͷੑೳΛେ෯ʹ௒͑Δ
  8. • [LFRR](Neve 2019) Latent Factor Models and Aggregation Operator for

    Collaborative Filtering in Reciprocal Recommender Systems • ߦಈཤྺʹج͖ͮ࡞੒ͨ͠ User-User ߦྻʹ Matrix Factorization Λద༻ͯ͠ Preference Score Λࢉग़ • Aggregation Function ʹ͍ͭͯɼௐ࿨ฏۉҎ֎ͷؔ਺ʹ͍ͭͯ΋ൺֱ࣮ݧʢCross-Ratio Uninormʣ • ੑೳ͸ RCF (Xia 2015) ͱಉఔ౓͕ͩɼࣄલʹϞσϧΛֶश͓͚ͯ͠ΔͷͰߴ଎ ؔ࿈ݚڀ/طଘख๏ 2/2 https://speakerdeck.com/yuya4/latent-factor-models-and-aggregation-operators-for-collaborative- filtering-in-reciprocal-recommender-systems
  9. ʲ࿦จ঺հʳ*N3FD-FBSOJOH3FDJQSPDBM1SFGFSFODFT6TJOH*NBHFT J Neve, R McConville.2020. Proceedings of the 14th ACM

    Conference on Recommender Systems, 170-179.
  10. Backgrounds / Motivation • ૬ޓਪનγεςϜ͸·ͩ·ͩݚڀ͕ਐΜͰͳ͍ྖҬ • ڠௐϑΟϧλϦϯάΞϓϩʔνͷݚڀ͸͍͔ͭ͘ݟΒΕΔΑ͏ʹͳ͕ͬͨɺ಺༰ϕʔεϑΟϧλϦϯ άΞϓϩʔνͷݚڀ͸ RECON (Pizzato

    2010) Ҏ߱͋·ΓਐΜͰ͍ͳ͍ • RECON ͸ϓϩϑΟʔϧͷΧςΰϦσʔλͷΈΛར༻ͨ͠΋ͷ • ҰํͰɺσʔςΟϯάαʔϏεʹ͓͍ͯը૾͸େมॏཁͳཁૉɻϓϩϑΟʔϧͷςΩετ৘ใΛݟͣ ʹը૾͚ͩͰ޷͖ݏ͍Λ൑அ͢Δ͜ͱ͕ଟ͍ͱ͍͏σʔλ΋ɻʢTinder ͷྫΛग़͍ͯͨ͠ʣ ը૾σʔλΛ༻͍ͨ಺༰ϕʔεϑΟϧλϦϯάͷΞϧΰϦζϜͷఏҊ
  11. Contributions 1. ը૾σʔλͱᅂ޷σʔλʹجͮ͘ personal attractiveness (not general attractivenessʣͷ༧ଌϞσϧͷ࡞੒ 2. personal

    attractiveness ϕʔεͷ૬ޓਪનγεςϜʢImRecʣͷߏங 3. ࣮ࡏ͢ΔσʔςΟϯάαʔϏεʢpairsʣͷσʔλΛ༻͍ͯੑೳͷݕূΛߦ͍ɺ RECON Λ௒͑ΔੑೳΛ֬ೝ personal attractiveness: how attractive is 's image to user general attractiveness: how attractive is to the average potential partner y x y
  12. Network: predicting personal attractiveness • Ϣʔβ ʹରͯ͠ɺ ͕ Like ͨ͠Ϣʔβ

    (anchor user)ɺ ͱ͸ผͷ ͕ Like ͨ͠Ϣʔβ ɺ ͕ Nope ͨ͠Ϣʔβ ͱ͍͏ triplet Λ࡞੒ • → 1ɺ → 0 ͱͳΔΑ͏ʹɺͦΕͧΕͷϢʔβͷը૾Λೖྗͱͯ͠ Siamese Network Λֶश • ͕ Like ͨ͠ϢʔβͲ͏͕ۙ͘͠ɺLike ͨ͠Ϣʔβͱ Nope ͨ͠Ϣʔβ͕ԕ͘ͳΔΑ͏ʹֶश • 200,000 ϖΞͷإࣸਅΛར༻ • 100,000 ͸ޓ͍ʹ Like ͯ͠ Match ͨ͠΋ͷɺ100,000 ͸Ұํ͸ Like ͯ͠΋͏Ұํ͕ Nope ͨ͠΋ͷ x x ya ya x yp x yn (ya , yp ) (ya , yn ) x ڞ௨ W
  13. Recommender Systems Architecture 1. Ϣʔβ ͱϢʔβ ͷϖΞʹରͯ͠ɺͦΕͧΕͷϢʔβ ͕ Like ͨ͠ϢʔβΛूΊΔʢ্ݶ30݅ʣ

    2. ( → Λߟ͑Δ) ͷը૾Λ ɺ ͕ Like ͨ͠ը૾Λ ͱͯ͠ɺ ʹର͢Δग़ྗʢෳ਺ʣΛ֫ಘ 3. ෳ਺ͷ ʹର͢Δग़ྗΛ̍ͭͷ Preference Score ʹ aggregate ͢Δʢࣄલʹ܇࿅͓͍ͯͨ͠ RFʣ 4. → ɺ ̎ͭͷ Preference Score Λ Aggregate ʢௐ࿨ฏۉʣͯ͠ɺReciprocal Preference Score Λ֫ಘ x y x y y ya x yp (ya , yp ) (ya , yp ) x y y → x
  14. Experiments • ϓϩϑΟʔϧͷΧςΰϦσʔλʹج͍ͮͨ಺༰ϕʔεͷ RECON ͱͷൺֱ࣮ݧ • ڠௐϑΟϧλϦϯάϕʔεͷ LFRR ͱͷൺֱ࣮ݧ •

    ಛʹɺcold-start ͷঢ়گʹ͓͚ΔൺֱΛߦͬͨ • ʢCV on 20,000 pairs of usersʣ
  15. Result ᶃ ImRec vs RECON • ImRec ͷํ͕େ͖͘ྑ͍݁Ռʹ • RECON

    ͸΄΅ϥϯμϜͳਪનͱಉ͘͡Β͍ͷਫ਼౓ʹ • RECON ͷΦϦδφϧͳ࣮ݧͰ༻͍ΒΕͨσʔληο τ͸ɺϓϩϑΟʔϧ৘ใ͕ॏཁͳ΋ͷͰ͋ͬͨʢը૾ σʔλ͸ͳ͔ͬͨʁʣ
  16. Result ᶄ ImRec vs LFRR (cold-start situation) • cold-start ͷঢ়گΛγϛϡϨʔγϣϯ͢ΔͨΊʹɺ

    Ϣʔβ͋ͨΓͷᅂ޷σʔλͷ਺ʹ੍ݶΛֶ͔͚ͯश ΛߦͬͨϞσϧͰൺֱ࣮ݧ • Indicator: ̍Ϣʔβ͋ͨΓͷ Like ͱ Nope ͷσʔλ ͕ ݸͣͭ • ֶशσʔλ͕গͳ͍ͱ͖ʢcold-start ͕ݦஶͳͱ ͖ʣɺLFRR ͸΄΅ϥϯμϜͳਪનͱಉ͘͡Β͍ͷਫ਼ ౓͕ͩɺImRec ͸ͦ͜·Ͱਫ਼౓͕མͪͳ͍ • ֶशσʔλ͕૿͑ͯ͘ΔͱɺLFRR ͷਫ਼౓ͷํ͕ྑ͘ ͳ͍ͬͯ͘ • ॳճମݧ͕ॏཁͳσʔςΟϯάΞϓϦͰ͸ cold-start ໰୊΁ͷରॲ͕େ੾ͳͷͰɺ͜ΕΒΛ͏·͘૊Έ߹ Θ͍ͤͯ͘ඞཁ K K
  17. Conclusions • ը૾ʹج͍ͮͨ personal attractiveness Λ༧ଌ͢ΔϞσϧΛ࡞੒ͨ͠ɻ • ImRec ͸ίϯςϯπϕʔεͷ RRSs

    ͷϕʔεϥΠϯͰ͋Δ RECON ͷੑೳΛ্ճͬͨɻ • ڠௐϑΟϧλϦϯάϕʔεͷ RRSs ʹରͯ͠ɺcold-start ͳঢ়گʹ͓͍ͯੑೳΛ্ճͬͨɻ