MATRI A MultiAspect and Transitive Trust Inference Model

MATRI: A Multi-Aspect and Transitive Trust Inference Model Yuan Yao Joint work with Hanghang Tong, Xifeng Yan, Feng Xu, and Jian Lu May 13 -17, WWW 2013 1

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 2

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 3

Trust “Trust is the subjective probability by which an individual (trustor), expects that another individual (trustee) will perform well on a given action. ” 4

Trust Inference Bob : Trust How to infer the unknown trust relationships? Alice Carol E. g. , to what extent should Bob trust Elva? Elva David Trust Properties: Transitivity, Multi-Aspect, Trust Bias 5

P 1: Trust Transitivity Bob Alice Bob -> Elva (TBE)? TBA TAE Carol Trust transitivity (or trust propagation): TBE = TBA * TAE Elva David 6

P 2: Multi-Aspect Trustor Preferences Trustee Capabilities Bob -> Elva (TBE)? 7

P 3: Trust Bias Overall avg. rating: 0. 5 Trustor bias: Alice Bob Carol David Elva 0. 2 Trustee -0. 1 bias: 0. 4 0. 2 Bob -> Elva (TBE)? -0. 3 -0. 1 0. 2 0. 1 -0. 2 TBE = 0. 4 - 0. 2 + 0. 5 = 0. 7 8

This Paper n n n Q 1: how to characterize multi-aspect trust directly from trust ratings? Q 2: how to incorporate trust bias? Q 3: how to incorporate trust transitivity? 9

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 10

Modeling Multi-Aspect -> user -- > item rating -> item 11

Modeling Multi-Aspect 12

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 13

Incorporating Trust Bias n Three types of trust bias: ¡ Global bias (μ), trustor bias (x), trustee bias (y) 14

Computing Bias Global Bias: Trustor Bias: Trustee Bias: 15

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 16

Incorporating Trust Transitivity n Four types of trust propagation : known trust : inferred trust (a) T * T (b) T ’ (c) T ’ * T (d) T * T ’ (i, j) Zij 17

Computing Propagation : (zij) 18

Our Final Model: Ma. Tr. I Trust bias Trust transitivity Multi-Aspect 19

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 20

Experiments n Datasets ¡ ¡ n n Advogato (http: //www. trustlet. org/wiki/Advogato_dataset ) PGP (Pretty Good Privacy) Effectiveness: how accurate is the proposed MATRI for trust inference? Efficiency: how fast is the proposed MATRI? 21

Effectiveness Results Comparisons with trust propagation models. (better) Our method 22

Effectiveness Results Comparisons with related methods. Smaller is better. Our method HCD: C. Hsieh et al. , Low rank modeling of signed networks. KDD 2012. KBV: Y. Koren et al. , Matrix factorization techniques for recommender 23 systems. Computer 2009

Efficiency Results Pre-computational time: O(m+n) Online response time: O(1) Our method 24

Roadmap n n n Background and Motivations Modeling Multi-Aspect Incorporating Trust Bias Incorporating Trust Transitivity Empirical Evaluations Conclusions 25

Conclusions An Integral Trust-Inference Model p ¡ p ¡ Q 1: how to characterize multi-aspect? A 1: analogy to recommendation problem Q 2: how to incorporate trust bias? A 2: treat bias as specified factors Q 3: how to incorporate trust transitivity? A 3: propagation through factorization Empirical Evaluations p p Effectiveness: >10% improvement Efficiency: p p linear in pre-computation constant online response 26

Thanks！ Q&A 27