TY - GEN
T1 - Node, motif and subgraph
T2 - 10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
AU - Yang, Carl
AU - Liu, Mengxiong
AU - Zheng, Vincent W.
AU - Han, Jiawei
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/24
Y1 - 2018/10/24
N2 - Networks or graphs provide a natural and generic way for modeling rich structured data. Recent research on graph analysis has been focused on representation learning, of which the goal is to encode the network structures into distributed embedding vectors, so as to enable various downstream applications through off-the-shelf machine learning. However, existing methods mostly focus on node-level embedding, which is insufficient for subgraph analysis. Moreover, their leverage of network structures through path sampling or neighborhood preserving is implicit and coarse. Network motifs allow graph analysis in a finer granularity, but existing methods based on motif matching are limited to enumerated simple motifs and do not leverage node labels and supervision. In this paper, we develop NEST, a novel hierarchical network embedding method combining motif filtering and convolutional neural networks. Motif-based filtering enables NEST to capture exact small structures within networks, and convolution over the filtered embedding allows it to fully explore complex substructures and their combinations. NEST can be trivially applied to any domain and provide insight into particular network functional blocks. Extensive experiments on protein function prediction, drug toxicity prediction and social network community identification have demonstrated its effectiveness and efficiency.
AB - Networks or graphs provide a natural and generic way for modeling rich structured data. Recent research on graph analysis has been focused on representation learning, of which the goal is to encode the network structures into distributed embedding vectors, so as to enable various downstream applications through off-the-shelf machine learning. However, existing methods mostly focus on node-level embedding, which is insufficient for subgraph analysis. Moreover, their leverage of network structures through path sampling or neighborhood preserving is implicit and coarse. Network motifs allow graph analysis in a finer granularity, but existing methods based on motif matching are limited to enumerated simple motifs and do not leverage node labels and supervision. In this paper, we develop NEST, a novel hierarchical network embedding method combining motif filtering and convolutional neural networks. Motif-based filtering enables NEST to capture exact small structures within networks, and convolution over the filtered embedding allows it to fully explore complex substructures and their combinations. NEST can be trivially applied to any domain and provide insight into particular network functional blocks. Extensive experiments on protein function prediction, drug toxicity prediction and social network community identification have demonstrated its effectiveness and efficiency.
UR - http://www.scopus.com/inward/record.url?scp=85057313862&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85057313862&partnerID=8YFLogxK
U2 - 10.1109/ASONAM.2018.8508729
DO - 10.1109/ASONAM.2018.8508729
M3 - Conference contribution
AN - SCOPUS:85057313862
T3 - Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
SP - 47
EP - 52
BT - Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
A2 - Tagarelli, Andrea
A2 - Reddy, Chandan
A2 - Brandes, Ulrik
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 August 2018 through 31 August 2018
ER -