Abstract

Networked prediction has attracted lots of research attention in recent years. Compared with the traditional learning setting, networked prediction is even harder to understand due to its coupled, multi-level nature. The learning process propagates top-down through the underlying network from the macro level (the entire learning system), to meso level (learning tasks), and to micro level (individual learning examples). In the meanwhile, the networked prediction setting also offers rich context to explain the learning process through the lens of multi-aspect, including training examples (e.g., what are the most influential examples), the learning tasks (e.g., which tasks are most important) and the task network (e.g., which task connections are the keys). Thus, we propose a multi-aspect, multi-level approach to explain networked prediction. The key idea is to efficiently quantify the influence on different levels the learning system due to the perturbation of various aspects. Th proposed method offers two distinctive advantages: (1) multi-aspe multi-level: it is able to explain networked prediction from multip aspects (i.e., example-task-network) at multiple levels (i.e., macr meso-micro); (2) efficiency: it has a linear complexity by efficient evaluating the influences of changes to the networked predictio without retraining.

Original languageEnglish (US)
Title of host publicationCIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management
EditorsNorman Paton, Selcuk Candan, Haixun Wang, James Allan, Rakesh Agrawal, Alexandros Labrinidis, Alfredo Cuzzocrea, Mohammed Zaki, Divesh Srivastava, Andrei Broder, Assaf Schuster
PublisherAssociation for Computing Machinery
Pages1819-1822
Number of pages4
ISBN (Electronic)9781450360142
DOIs
StatePublished - Oct 17 2018
Event27th ACM International Conference on Information and Knowledge Management, CIKM 2018 - Torino, Italy
Duration: Oct 22 2018Oct 26 2018

Other

Other27th ACM International Conference on Information and Knowledge Management, CIKM 2018
CountryItaly
CityTorino
Period10/22/1810/26/18

Fingerprint

Prediction
Learning process
Learning systems
Top-down
Perturbation
Multilevel approach
Individual learning
Retraining
Nature

Keywords

  • Explainable Networked Prediction
  • Influence Function

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Li, L., Tong, H., & Liu, H. (2018). Towards explainable networked prediction. In N. Paton, S. Candan, H. Wang, J. Allan, R. Agrawal, A. Labrinidis, A. Cuzzocrea, M. Zaki, D. Srivastava, A. Broder, ... A. Schuster (Eds.), CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management (pp. 1819-1822). Association for Computing Machinery. https://doi.org/10.1145/3269206.3269276

Towards explainable networked prediction. / Li, Liangyue; Tong, Hanghang; Liu, Huan.

CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ed. / Norman Paton; Selcuk Candan; Haixun Wang; James Allan; Rakesh Agrawal; Alexandros Labrinidis; Alfredo Cuzzocrea; Mohammed Zaki; Divesh Srivastava; Andrei Broder; Assaf Schuster. Association for Computing Machinery, 2018. p. 1819-1822.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, L, Tong, H & Liu, H 2018, Towards explainable networked prediction. in N Paton, S Candan, H Wang, J Allan, R Agrawal, A Labrinidis, A Cuzzocrea, M Zaki, D Srivastava, A Broder & A Schuster (eds), CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, pp. 1819-1822, 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, Torino, Italy, 10/22/18. https://doi.org/10.1145/3269206.3269276
Li L, Tong H, Liu H. Towards explainable networked prediction. In Paton N, Candan S, Wang H, Allan J, Agrawal R, Labrinidis A, Cuzzocrea A, Zaki M, Srivastava D, Broder A, Schuster A, editors, CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2018. p. 1819-1822 https://doi.org/10.1145/3269206.3269276
Li, Liangyue ; Tong, Hanghang ; Liu, Huan. / Towards explainable networked prediction. CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. editor / Norman Paton ; Selcuk Candan ; Haixun Wang ; James Allan ; Rakesh Agrawal ; Alexandros Labrinidis ; Alfredo Cuzzocrea ; Mohammed Zaki ; Divesh Srivastava ; Andrei Broder ; Assaf Schuster. Association for Computing Machinery, 2018. pp. 1819-1822
@inproceedings{142e096a4dd64b04aff41295a58958ab,
title = "Towards explainable networked prediction",
abstract = "Networked prediction has attracted lots of research attention in recent years. Compared with the traditional learning setting, networked prediction is even harder to understand due to its coupled, multi-level nature. The learning process propagates top-down through the underlying network from the macro level (the entire learning system), to meso level (learning tasks), and to micro level (individual learning examples). In the meanwhile, the networked prediction setting also offers rich context to explain the learning process through the lens of multi-aspect, including training examples (e.g., what are the most influential examples), the learning tasks (e.g., which tasks are most important) and the task network (e.g., which task connections are the keys). Thus, we propose a multi-aspect, multi-level approach to explain networked prediction. The key idea is to efficiently quantify the influence on different levels the learning system due to the perturbation of various aspects. Th proposed method offers two distinctive advantages: (1) multi-aspe multi-level: it is able to explain networked prediction from multip aspects (i.e., example-task-network) at multiple levels (i.e., macr meso-micro); (2) efficiency: it has a linear complexity by efficient evaluating the influences of changes to the networked predictio without retraining.",
keywords = "Explainable Networked Prediction, Influence Function",
author = "Liangyue Li and Hanghang Tong and Huan Liu",
year = "2018",
month = "10",
day = "17",
doi = "10.1145/3269206.3269276",
language = "English (US)",
pages = "1819--1822",
editor = "Norman Paton and Selcuk Candan and Haixun Wang and James Allan and Rakesh Agrawal and Alexandros Labrinidis and Alfredo Cuzzocrea and Mohammed Zaki and Divesh Srivastava and Andrei Broder and Assaf Schuster",
booktitle = "CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Towards explainable networked prediction

AU - Li, Liangyue

AU - Tong, Hanghang

AU - Liu, Huan

PY - 2018/10/17

Y1 - 2018/10/17

N2 - Networked prediction has attracted lots of research attention in recent years. Compared with the traditional learning setting, networked prediction is even harder to understand due to its coupled, multi-level nature. The learning process propagates top-down through the underlying network from the macro level (the entire learning system), to meso level (learning tasks), and to micro level (individual learning examples). In the meanwhile, the networked prediction setting also offers rich context to explain the learning process through the lens of multi-aspect, including training examples (e.g., what are the most influential examples), the learning tasks (e.g., which tasks are most important) and the task network (e.g., which task connections are the keys). Thus, we propose a multi-aspect, multi-level approach to explain networked prediction. The key idea is to efficiently quantify the influence on different levels the learning system due to the perturbation of various aspects. Th proposed method offers two distinctive advantages: (1) multi-aspe multi-level: it is able to explain networked prediction from multip aspects (i.e., example-task-network) at multiple levels (i.e., macr meso-micro); (2) efficiency: it has a linear complexity by efficient evaluating the influences of changes to the networked predictio without retraining.

AB - Networked prediction has attracted lots of research attention in recent years. Compared with the traditional learning setting, networked prediction is even harder to understand due to its coupled, multi-level nature. The learning process propagates top-down through the underlying network from the macro level (the entire learning system), to meso level (learning tasks), and to micro level (individual learning examples). In the meanwhile, the networked prediction setting also offers rich context to explain the learning process through the lens of multi-aspect, including training examples (e.g., what are the most influential examples), the learning tasks (e.g., which tasks are most important) and the task network (e.g., which task connections are the keys). Thus, we propose a multi-aspect, multi-level approach to explain networked prediction. The key idea is to efficiently quantify the influence on different levels the learning system due to the perturbation of various aspects. Th proposed method offers two distinctive advantages: (1) multi-aspe multi-level: it is able to explain networked prediction from multip aspects (i.e., example-task-network) at multiple levels (i.e., macr meso-micro); (2) efficiency: it has a linear complexity by efficient evaluating the influences of changes to the networked predictio without retraining.

KW - Explainable Networked Prediction

KW - Influence Function

UR - http://www.scopus.com/inward/record.url?scp=85058036460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058036460&partnerID=8YFLogxK

U2 - 10.1145/3269206.3269276

DO - 10.1145/3269206.3269276

M3 - Conference contribution

SP - 1819

EP - 1822

BT - CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management

A2 - Paton, Norman

A2 - Candan, Selcuk

A2 - Wang, Haixun

A2 - Allan, James

A2 - Agrawal, Rakesh

A2 - Labrinidis, Alexandros

A2 - Cuzzocrea, Alfredo

A2 - Zaki, Mohammed

A2 - Srivastava, Divesh

A2 - Broder, Andrei

A2 - Schuster, Assaf

PB - Association for Computing Machinery

ER -