TY - GEN
T1 - Mixed-transfer
T2 - 14th SIAM International Conference on Data Mining, SDM 2014
AU - Tan, Ben
AU - Zhong, Erheng
AU - NG, Kwok Po
AU - Yang, Qiang
N1 - Publisher Copyright:
Copyright © SIAM.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2014
Y1 - 2014
N2 - Heterogeneous transfer learning has been proposed as a new learning strategy to improve performance in a target domain by leveraging data from other heterogeneous source domains where feature spaces can be different across different domains. In order to connect two different spaces, one common technique is to bridge feature spaces by using some co-occurrence data. For example, annotated images can be used to build feature mapping from words to image features, and then applied on text-to-image knowledge transfer. However, in practice, such co-occurrence data are often from Web, e.g. Flickr, and generated by users. That means these data can be sparse and contain personal biases. Directly building models based on them may fail to provide reliable bridge. To solve these aforementioned problems, in this paper, we propose a novel algorithm named Mixed-Transfer. It is composed of three components, that is, a cross domain harmonic function to avoid personal biases, a joint transition probability graph of mixed instances and features to model the heterogeneous transfer learning problem, a random walk process to simulate the label propagation on the graph and avoid the data sparsity problem. We conduct experiments on 171 real-world tasks, showing that the proposed approach outperforms four state-of-the-art heterogeneous transfer learning algorithms.
AB - Heterogeneous transfer learning has been proposed as a new learning strategy to improve performance in a target domain by leveraging data from other heterogeneous source domains where feature spaces can be different across different domains. In order to connect two different spaces, one common technique is to bridge feature spaces by using some co-occurrence data. For example, annotated images can be used to build feature mapping from words to image features, and then applied on text-to-image knowledge transfer. However, in practice, such co-occurrence data are often from Web, e.g. Flickr, and generated by users. That means these data can be sparse and contain personal biases. Directly building models based on them may fail to provide reliable bridge. To solve these aforementioned problems, in this paper, we propose a novel algorithm named Mixed-Transfer. It is composed of three components, that is, a cross domain harmonic function to avoid personal biases, a joint transition probability graph of mixed instances and features to model the heterogeneous transfer learning problem, a random walk process to simulate the label propagation on the graph and avoid the data sparsity problem. We conduct experiments on 171 real-world tasks, showing that the proposed approach outperforms four state-of-the-art heterogeneous transfer learning algorithms.
KW - Co-occurrence data
KW - Heterogeneous transfer learning
KW - Random walk
UR - http://www.scopus.com/inward/record.url?scp=84959888323&partnerID=8YFLogxK
U2 - 10.1137/1.9781611973440.24
DO - 10.1137/1.9781611973440.24
M3 - Conference contribution
AN - SCOPUS:84959888323
T3 - SIAM International Conference on Data Mining 2014, SDM 2014
SP - 208
EP - 216
BT - SIAM International Conference on Data Mining 2014, SDM 2014
A2 - Zaki, Mohammed J.
A2 - Banerjee, Arindam
A2 - Parthasarathy, Srinivasan
A2 - Ning-Tan, Pang
A2 - Obradovic, Zoran
A2 - Kamath, Chandrika
PB - Society for Industrial and Applied Mathematics Publications
Y2 - 24 April 2014 through 26 April 2014
ER -