TY - GEN
T1 - MRMine
T2 - 28th ACM International Conference on Information and Knowledge Management, CIKM 2019
AU - Du, Boxin
AU - Tong, Hanghang
N1 - Funding Information:
7 ACKNOWLEDGEMENTS This material is supported by the National Science Foundation under Grant No. IIS-1651203, IIS-1715385, IIS-1743040, and CNS-1629888, by DTRA under the grant number HDTRA1-16-0017, by the United States Air Force and DARPA under contract number FA8750-17-C-0153 , by the U.S. Department of Homeland Security under Grant Award Number 2017-ST-061-QA0001 and by Army Research Office under the contract number W911NF-16-1-0168. The content of the information in this document does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/11/3
Y1 - 2019/11/3
N2 - Network embedding has become the cornerstone of a variety of mining tasks, such as classification, link prediction, clustering, anomaly detection and many more, thanks to its superior ability to encode the intrinsic network characteristics in a compact low-dimensional space. Most of the existing methods focus on a single network and/or a single resolution, which generate embeddings of different network objects (node/subgraph/network) from different networks separately. A fundamental limitation with such methods is that the intrinsic relationship across different networks (e.g., two networks share same or similar subgraphs) and that across different resolutions (e.g., the node-subgraph membership) are ignored, resulting in disparate embeddings. Consequentially, it leads to sub-optimal performance or even becomes inapplicable for some downstream mining tasks (e.g., role classification, network alignment. etc.). In this paper, we propose a unified framework (MrMine) to learn the representations of objects from multiple networks at three complementary resolutions (i.e., network, subgraph and node) simultaneously. The key idea is to construct the cross-resolution cross-network context for each object. The proposed method bears two distinctive features. First, it enables and/or boosts various multi-network downstream mining tasks by having embeddings at different resolutions from different networks in the same embedding space. Second, Our method is efficient and scalable, with a O(nloд(n)) time complexity for the base algorithm and a linear time complexity w.r.t. the number of nodes and edges of input networks for the accelerated version. Extensive experiments on real-world data show that our methods (1) are able to enable and enhance a variety of multi-network mining tasks, and (2) scale up to million-node networks.
AB - Network embedding has become the cornerstone of a variety of mining tasks, such as classification, link prediction, clustering, anomaly detection and many more, thanks to its superior ability to encode the intrinsic network characteristics in a compact low-dimensional space. Most of the existing methods focus on a single network and/or a single resolution, which generate embeddings of different network objects (node/subgraph/network) from different networks separately. A fundamental limitation with such methods is that the intrinsic relationship across different networks (e.g., two networks share same or similar subgraphs) and that across different resolutions (e.g., the node-subgraph membership) are ignored, resulting in disparate embeddings. Consequentially, it leads to sub-optimal performance or even becomes inapplicable for some downstream mining tasks (e.g., role classification, network alignment. etc.). In this paper, we propose a unified framework (MrMine) to learn the representations of objects from multiple networks at three complementary resolutions (i.e., network, subgraph and node) simultaneously. The key idea is to construct the cross-resolution cross-network context for each object. The proposed method bears two distinctive features. First, it enables and/or boosts various multi-network downstream mining tasks by having embeddings at different resolutions from different networks in the same embedding space. Second, Our method is efficient and scalable, with a O(nloд(n)) time complexity for the base algorithm and a linear time complexity w.r.t. the number of nodes and edges of input networks for the accelerated version. Extensive experiments on real-world data show that our methods (1) are able to enable and enhance a variety of multi-network mining tasks, and (2) scale up to million-node networks.
KW - Cross-resolution cross-network context
KW - Multi-network mining
KW - Network embedding
KW - Unified framework
UR - http://www.scopus.com/inward/record.url?scp=85075479646&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075479646&partnerID=8YFLogxK
U2 - 10.1145/3357384.3357944
DO - 10.1145/3357384.3357944
M3 - Conference contribution
AN - SCOPUS:85075479646
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 479
EP - 488
BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
Y2 - 3 November 2019 through 7 November 2019
ER -