TY - GEN
T1 - Domain Adaptation in Physical Systems via Graph Kernel
AU - Li, Haoran
AU - Tong, Hanghang
AU - Weng, Yang
N1 - Funding Information:
This work is supported by Nation Science Foundation (NSF) under grants No. 1947135, No. 2134079, No. 1939725, ECCS-1810537, and ECCS-2048288, and the Department of Energy (DOE) under grants DE-AR00001858-1631 and DE-EE0009355.
Publisher Copyright:
© 2022 ACM.
PY - 2022/8/14
Y1 - 2022/8/14
N2 - Physical systems are extending their monitoring capacities to edge areas with low-cost, low-power sensors and advanced data mining and machine learning techniques. However, new systems often have limited data for training the model, calling for effective knowledge transfer from other relevant grids. Specifically, Domain Adaptation (DA) seeks domain-invariant features to boost the model performance in the target domain. Nonetheless, existing DA techniques face significant challenges due to the unique characteristics of physical datasets: (1) complex spatial-temporal correlations, (2) diverse data sources including node/edge measurements and labels, and (3) large-scale data sizes. In this paper, we propose a novel cross-graph DA based on two core designs of graph kernels and graph coarsening. The former design handles spatial-temporal correlations and can incorporate networked measurements and labels conveniently. The spatial structures, temporal trends, measurement similarity, and label information together determine the similarity of two graphs, guiding the DA to find domain-invariant features. Mathematically, we construct a Graph kerNel-based distribution Adaptation (GNA) with a specifically-designed graph kernel. Then, we prove the proposed kernel is positive definite and universal, which strictly guarantees the feasibility of the used DA measure. However, the computation cost of the kernel is prohibitive for large systems. In response, we propose a novel coarsening process to obtain much smaller graphs for GNA. Finally, we report the superiority of GNA in diversified systems, including power systems, mass-damper systems, and human-activity sensing systems.
AB - Physical systems are extending their monitoring capacities to edge areas with low-cost, low-power sensors and advanced data mining and machine learning techniques. However, new systems often have limited data for training the model, calling for effective knowledge transfer from other relevant grids. Specifically, Domain Adaptation (DA) seeks domain-invariant features to boost the model performance in the target domain. Nonetheless, existing DA techniques face significant challenges due to the unique characteristics of physical datasets: (1) complex spatial-temporal correlations, (2) diverse data sources including node/edge measurements and labels, and (3) large-scale data sizes. In this paper, we propose a novel cross-graph DA based on two core designs of graph kernels and graph coarsening. The former design handles spatial-temporal correlations and can incorporate networked measurements and labels conveniently. The spatial structures, temporal trends, measurement similarity, and label information together determine the similarity of two graphs, guiding the DA to find domain-invariant features. Mathematically, we construct a Graph kerNel-based distribution Adaptation (GNA) with a specifically-designed graph kernel. Then, we prove the proposed kernel is positive definite and universal, which strictly guarantees the feasibility of the used DA measure. However, the computation cost of the kernel is prohibitive for large systems. In response, we propose a novel coarsening process to obtain much smaller graphs for GNA. Finally, we report the superiority of GNA in diversified systems, including power systems, mass-damper systems, and human-activity sensing systems.
KW - domain adaptation
KW - graph coarsening
KW - graph kernels
KW - networked data
KW - physical system
UR - http://www.scopus.com/inward/record.url?scp=85137143458&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137143458&partnerID=8YFLogxK
U2 - 10.1145/3534678.3539380
DO - 10.1145/3534678.3539380
M3 - Conference contribution
AN - SCOPUS:85137143458
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 868
EP - 876
BT - KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
T2 - 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Y2 - 14 August 2022 through 18 August 2022
ER -