LIME

Transcript

1. 1.

   LIME Masaaki Horikoshi @ ARISE analytics

2. 2.

   ࣗݾ঺հ • R • ύοέʔδ։ൃͳͲ • Git Awards ࠃ಺1Ґ •

   Python • http://git-awards.com/users/search?login=sinhrks
3. 3.

   Α͋͘Δ͜ͱ ΤʔΞΠͰ͍͍ײ͡ʹ΍ͬͱ͍ͯΑʂ
   ݁Ռ͕ྑ͚Ε͹த਎͸ؾʹ͠ͳ͍Αʂʂ Ͱɺ͜Εͬͯ݁ہͲ͏͍͏͜ͱͳͷʁ
   த਎͕Θ͔Βͳ͍΋ͷ͸࢖͑ͳ͍Αʂʂʂ ͑Β͍ਓ ˞΁ʔγϟͰ͸ͳ͍ ݁Ռ͕ग़Δͱʜ

4. 4.

   Interpretability ղऍՄೳੑ

5. 5.

   ղऍͷͨΊͷΞϓϩʔν 1. આ໌͠΍͍͢ػցֶशख๏ΛબͿ • ਫ਼౓͕ෆे෼ͳ৔߹͕͋Δ 2. ػցֶशख๏ʹΑΒͳ͍ղऍख๏Λ࢖͏

6. 6.

   ղऍՄೳੑ • Global Interpretability • Ϟσϧ΍σʔλશମͷ܏޲Λղऍ • ۙࣅ΍ཁ໿౷ܭྔΛར༻ => ہॴతʹ͸ෆਖ਼֬ͳ৔߹΋

   • Local Interpretability • Ϟσϧ΍σʔλͷݶΒΕͨྖҬΛղऍ • ΑΓਖ਼֬ͳઆ໌͕Մೳ
7. 7.

   ղऍՄೳੑ • ద੾ͳख๏͸ʮԿΛʯղऍ͍͔ͨ͠ʹґଘ .PEFM
   4QFDJpD .PEFM
   "HOPTUJD (MPCBM
   *OUFSQSFUBCJMJUZ w 3FHSFTTJPO
   $PF⒏DJFOUT
   w

   'FBUVSF
   *NQPSUBODF
   ʜ w 4VSSPHBUF
   .PEFMT
   w 4FOTJUJWJUZ
   "OBMZTJT
   ʜ -PDBM
   *OUFSQSFUBCJMJUZ w .BYJNVN
   "DUJWBUJPO
   "OBMZTJT
   ʜ w -*.&
   w -0$0
   w 4)"1
   ʜ
8. 8.

   LIMEͱ͸ʁ

9. 9.

   Local Interpretable Model-agnostic Explanations

10. 10.

    LIME • “Why Should I Trust You?” Explaining the Predictions

    of Any Classifier (2016) • Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
11. 11.

    LIME • LIME͸ҎԼͷؔ਺Λ΋ͱʹσʔλ x ͷղऍΛಘΔ • G: ղऍ༻ͷֶशثͷू߹ • L:

    ղऍֶ͍ͨ͠शثͱղऍ༻ͷֶशثͷ ΠxͷݩͰͷࠩ • f: ղऍֶ͍ͨ͠शث • Πx: σʔλ x ͱͷྨࣅ౓ • Ω: ղऍ༻ͷֶशثͷෳࡶ͞ʹର͢Δേଇ߲ • ۩ମతखஈ͸υϝΠϯʹґଘ
12. 12.

    ςʔϒϧσʔλɾ෼ྨ໰୊ͷྫ • σʔλ x ͷपลͰαϯϓϦϯά • طఆͰ5,000 • αϯϓϦϯάํ๏͸ม਺ͷछྨʹґଘ •

    Exponential KernelͰॏΈ෇͚ • ม਺બ୒ • Forward/Backward, LARSͳͲ • RidgeճؼͳͲ ˞1ZUIPO࣮૷ ޙड़ ʹ΋ͱͮ͘
13. 13.

    ύοέʔδ • Python • ࿦จஶऀ࡞ • https://github.com/marcotcr/lime • R •

    ্هͷϙʔςΟϯά • https://github.com/thomasp85/lime install.packages(‘lime’)
14. 14.

    LIME (R) • αϯϓϧ library(caret) library(lime) model <- train(iris[-5], iris[[5]],

    method = 'rf') explainer <- lime(iris[-5], model) explanations <- explain(iris[1, -5], explainer, n_labels = 1, n_features = 2) explanations model_type case label label_prob model_r2 model_intercept 1 classification 1 setosa 1 0.3776584 0.2544468 2 classification 1 setosa 1 0.3776584 0.2544468 model_prediction feature feature_value feature_weight feature_desc 1 0.7113922 Sepal.Width 3.5 0.02101138 3.3 < Sepal.Width 2 0.7113922 Petal.Length 1.4 0.43593404 Petal.Length <= 1.60 data prediction 1 5.1, 3.5, 1.4, 0.2 1, 0, 0 2 5.1, 3.5, 1.4, 0.2 1, 0, 0 ֶशثΛ܇࿅ ղऍ༻ͷΫϥεΛ࡞੒ ղऍΛग़ྗ
15. 15.

    LIME (R) plot_features(explanations) ղऍΛϓϩοτ

16. 16.

    Enjoy!