Explaining rankings - Maartje ter Hoeve...LIME (Ribeiro et al, 2016): find a local, faithful...

Explaining rankings

Maartje ter HoeveUniversity of Amsterdam & Blendle

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

C o n t e n t

What and why?

RankingsResearch questions

Related workAnswering research questions

Discussion and Conclusion

Blendle

C o n t e n t

What and why?

Discussion and conclusion

Blendle

I n t r o d u c t i o n

What is explainability and why is it needed?

E x p l a i n a b i l i t y : w h a t a n d w h y ?

User Developer

B u t w h a t i s a n e x p l a n a t i o n ?

An explanation needs to faithfully give the underlying cause of an event

B u t w h a t i s a n e x p l a n a t i o n ?

Justification

Provide conceptual explanations that do not necessarily expose the underlying structure of the algorithm

Description

Provide conceptual explanations that do expose the underlying structure of the algorithm

C o n t e n t

What and why?

Blendle

R a n k i n g s

H o w d o w e e x p l a i n a r a n k i n g ?

Only looking at the score of an item is not sufficient

C o n t e n t

What and why?

Blendle

B l e n d l e

Blendle already has heuristic justifications

We use these as one of our baselines

C o n t e n t

What and why?

Blendle

R e s e a r c h q u e s t i o n s

RQ2 What way of showing news recommendations reasons do users prefer: textual or visual reasons; a single reason or multiple

reasons; apparent or less apparent reasons?

PART 1

RQ1 Do users want to receive explanations of why particular news items are recommended to them?

R e s e a r c h q u e s t i o n s

RQ3 How do we provide users with easy to understand, uncluttered, listwise explanations?

RQ4 How do we build an explanation system that produces faithful, model-agnostic explanations for the outcome of a ranking

algorithm, yet is scalable so that it can run in real time?

RQ5 Does the reading behaviour of users who are provided with model-agnostic listwise explanations for a personalized ranked

selection of news articles differ from the reading behaviour of users who are provided with heuristic or pointwise explanations for a

personalized ranked selection of news articles?

PART 2

C o n t e n t

What and why?

Blendle

R e l a t e d w o r k

LIME (Ribeiro et al, 2016): find a local, faithful explanation for the decision of any classifier

LIME is a baseline of this research

We work with rankings, not classifiers

Therefore we bin our ranking scores

C o n t e n t

What and why?

Blendle

P a r t 1 - U s e r s t u d y

Single Reason - Visible Single Reason - Invisible Multiple Reasons - Visible Multiple Reasons - Combined Bar chart

179 sent type 1180 sent type 2182 sent type 3

41 answered type 136 answered type 243 answered type 3

R Q 1 D o u s e r s w a n t e x p l a n a t i o n s ?

User wants reasons Times answered

Yes 65

Somewhat 24

I don't know 5

X2 = 14.55, p < 0.001

Single Reason - Visible Single Reason - Invisible Multiple Reasons - Visible Multiple Reasons - Combined Bar chart

R Q 2 P r e f e r e n c e s h o w e x p l a n a t i o n s a r e s h o w n ?

Transparency

Sufficiency

Satisfaction

P a r t 2

R Q 3 H o w d o w e m a k e l i s t w i s e e x p l a n a t i o n s ?

Explain the entire list?

Explain items in comparison to other items?

Explain which features were important for the

position in the ranking?

Explain the entire list?

Explain items in comparison to other items?

Explain which features were important for the

position in the ranking?

f0 f1 f2 f3 f4

Which features are most important for the item's position in the ranking?

R Q 4 H o w d o w e d e s i g n t h i s ?

Main intuition

If we change feature values and the ranking changes, then this feature was important

Training phase

Find how feature values change the ranking

Find disruptive distributions and points of interests

Use distributions to sample feature values from

Find most important features

Return most important features as explanations

Explaining phase LISTEN - LISTwise ExplaiNer

Training phase

f0 f1 f2 f3 f4

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

f0 f1 f2 f3 f4

1 f1 f2 f3 f4

f0 f1 f2 f3 f4

2 f1 f2 f3 f4

f0 f1 f2 f3 f4

3 f1 f2 f3 f4

f0 f1 f2 f3 f4

4 f1 f2 f3 f4

f0 f1 f2 f3 f4

5 f1 f2 f3 f4

f0 f1 f2 f3 f4

6 f1 f2 f3 f4

f0 f1 f2 f3 f4

Find disruptive distributions and points of interests

Explanation phase

Find most important features

f0 f1 f2 f3 f4

Return most important features

Is this faithful?

Construct dummy data where we know what to expect

LISTEN gives the correct results

Disruptive distribution approach slightly decreases faithfulness, yet increases speed

This is still not fast enough to run in production

f0 f1 f2 …. fn-1 fn

Q-LISTEN

Same holds for mLIME

Q-mLIME

R Q 5 H o w d o u s e r s b e h a v e ?

A. Heuristic

A/B/C - test

B. Q-mLIME C. Q-LISTEN

Results

Heuristic Q-mLIME Q-LISTEN

% reasons seen (of total reads) 3.55 3.54 3.51

% reasons seen (of total reasons) 34.1 32.9 32.0

Reasons per user (of users that see reasons) 1.83 1.86 1.72

Article opened within 2 minutes (% of all reasons seen)

12.1 12.9 10.6

Reasons seen after 20 minutes of opening (% of all reasons seen)

11.0 10.1 10.7

C o n t e n t

What and why?

Blendle

C o n c l u s i o n a n d d i s c u s s i o n

RQ1 Do users want to receive explanations of why particular news items are recommended to them?

RQ2 What way of showing news recommendations reasons do users prefer: textual or visual reasons; a single reason or multiple

reasons; apparent or less apparent reasons?

PART 1

No specific one

RQ3 How do we provide users with easy to understand, uncluttered, listwise explanations?

RQ4 How do we build an explanation system that produces faithful, model-agnostic explanations for the outcome of a ranking

algorithm, yet is scalable so that it can run in real time?

PART 2

We look at which features were most important for an item's position in the ranking

We find feature importance by changing the feature values and changing the rankings

We make disruptive distributions

We learn the explanation space with a neural net

RQ5 Does the reading behaviour of users who are provided with model-agnostic listwise explanations for a personalized ranked

selection of news articles differ from the reading behaviour of users who are provided with heuristic or pointwise explanations for a

personalized ranked selection of news articles?

We do not find any significant differences

Take home message

Users clearly state that they want explanations. Therefore, even though their behaviour is not affected by the explanations,

still provide them with faithful explanations

R e a s o n s s e e n

L o s s a n d a c c u r a c y c u r v e s

m L I M E v s L I S T E N

A c t i v e a n d l e s s a c t i v e u s e r s

Explaining rankings - Maartje ter Hoeve...LIME (Ribeiro et al, 2016): find a local, faithful...

Documents

Trouwbrochure 2016 - De Orchideeën Hoeve

De Hoeve. - Mooi Wonen

Motions-Martin Ten Hoeve

Pres ict bekwaamheid-sdnl_301012 maartje

Jennifer Hoeve Hair - minimagazine - zomer 2015

Oss, Horzak Hoeve 3 (28 woningen)

Hoeve Nekum, Maastricht Wijngoed Apostelhoeve, …...2019/06/11 · Hoeve Nekum, Maastricht Methode Traditionelle Brut €53.50 Wijngoed Apostelhoeve, Maastricht 2018 Riesling 2018

30. Hoeve Hesselmans€¦ · /%+#"0#12#)%3456%/!"#$ %&'!"#$#%#&'('&)#) GP!"#$#%!#&&#'()&!"#$%&'$(()'(#*%'+,-#."")$'%#'/)(%0' Title: 30. Hoeve Hesselmans.pdf Created Date: 8/13/2019

LIME PRODUCTION PROCESS - hemptechglobal.com · LIMESTONE LIMESTONE CALCINATION LIME LIME PRODUCTION PROCESS Hydrator Lime milling Lime screening Classifier Milled lime Hydrated lime

Curing the Queue - Dissertation Maartje E. Zonderland

Douglas Gilmour, Yvonne Gootzen and Maartje Tummers

Baasjes kennel de hoeve

VISRESTAURANT HOEVE 7

John Ten Hoeve 9/11/13

4 Geld verdienen door jezelf te zijn - Amazon S3 · 2 Geld verdienen door jezelf te zijn – Manifesto . Maartje Koper Bewuste Creatie . Maartje Hoper . Maartje Hoper . Maartje Hoper

Automatic Summarization - Maartje ter Hoeve · Maartje ter Hoeve m.a.terhoeve@uva.nl @maartjeterhoeve 24 ROUGE Lin, Chin-Yew. “ROUGE: A Package for Automatic Evaluation of Summaries.”

Choosing Amsterdam (Carolien - Ocker - Mark - Maartje - Jessie)

Hospice de Duinsche Hoeve Jaarverslag 2020

Hotspots Family Report - Willem's Hoeve Rita

Rouwarrangementen | De Orchideeën Hoeve bv