Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

CrowNN: Human-in-the-loop Network with Crowd-generated Inputs

Abstract: 

Input features are indispensable for almost all machine learning methods; however, their definitions themselves are sometimes too abstract to extract automatically. Human-in-the- loop machine learning is a promising solution to such cases where humans extract the feature values for machine learning models. We use crowdsourcing for feature value extraction and consider a problem to aggregate the feature values to improve machine learning classifiers. We propose a novel neural network model called CROWNN, a neural network with crowd-generated inputs with the worker convolution layer, that learns both the capabilities of human feature extractors and the weights of a neural network classifier by applying the idea of the convolution neural network to feature aggregation. Our experiments using four datasets show the proposed method outperforms the baseline method using unsupervised aggregation methods in some datasets. We also show the robustness of the proposed model against the existence of spam workers, especially when they are malicious workers who intentionally flip the feature values.

up
0 users have voted:

Paper Details

Authors:
Yukino Baba, Hisashi Kashima
Submitted On:
10 May 2019 - 4:36am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Yusuke Sakata
Paper Code:
BD-P2
Document Year:
2019
Cite

Document Files

CROWNN_poster_icassp2019

(40)

Subscribe

[1] Yukino Baba, Hisashi Kashima, "CrowNN: Human-in-the-loop Network with Crowd-generated Inputs", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4289. Accessed: Sep. 20, 2019.
@article{4289-19,
url = {http://sigport.org/4289},
author = {Yukino Baba; Hisashi Kashima },
publisher = {IEEE SigPort},
title = {CrowNN: Human-in-the-loop Network with Crowd-generated Inputs},
year = {2019} }
TY - EJOUR
T1 - CrowNN: Human-in-the-loop Network with Crowd-generated Inputs
AU - Yukino Baba; Hisashi Kashima
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4289
ER -
Yukino Baba, Hisashi Kashima. (2019). CrowNN: Human-in-the-loop Network with Crowd-generated Inputs. IEEE SigPort. http://sigport.org/4289
Yukino Baba, Hisashi Kashima, 2019. CrowNN: Human-in-the-loop Network with Crowd-generated Inputs. Available at: http://sigport.org/4289.
Yukino Baba, Hisashi Kashima. (2019). "CrowNN: Human-in-the-loop Network with Crowd-generated Inputs." Web.
1. Yukino Baba, Hisashi Kashima. CrowNN: Human-in-the-loop Network with Crowd-generated Inputs [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4289