TY - GEN

T1 - Meta-Learned Metrics over Multi-Evolution Temporal Graphs

AU - Fu, Dongqi

AU - Fang, Liri

AU - MacIejewski, Ross

AU - Torvik, Vetle I.

AU - He, Jingrui

N1 - Publisher Copyright:
© 2022 ACM.

PY - 2022/8/14

Y1 - 2022/8/14

N2 - Graph metric learning methods aim to learn the distance metric over graphs such that similar (e.g., same class) graphs are closer and dissimilar (e.g., different class) graphs are farther apart. This is of critical importance in many graph classification applications such as drug discovery and epidemics categorization. Most, if not all, graph metric learning techniques consider the input graph as static, and largely ignore the intrinsic dynamics of temporal graphs. However, in practice, a graph typically has heterogeneous dynamics (e.g., microscopic and macroscopic evolution patterns). As such, labeling a temporal graph is usually expensive and also requires background knowledge. To learn a good metric over temporal graphs, we propose a temporal graph metric learning framework, Temp-GFSM. With only a few labeled temporal graphs, Temp-GFSM outputs a good metric that can accurately classify different temporal graphs and be adapted to discover new subspaces for unseen classes. Each proposed component in Temp-GFSM answers the following questions: What patterns are evolving in a temporal graph? How to weigh these patterns to represent the characteristics of different temporal classes? And how to learn the metric with the guidance from only a few labels? Finally, the experimental results on real-world temporal graph classification tasks from various domains show the effectiveness of our Temp-GFSM.

AB - Graph metric learning methods aim to learn the distance metric over graphs such that similar (e.g., same class) graphs are closer and dissimilar (e.g., different class) graphs are farther apart. This is of critical importance in many graph classification applications such as drug discovery and epidemics categorization. Most, if not all, graph metric learning techniques consider the input graph as static, and largely ignore the intrinsic dynamics of temporal graphs. However, in practice, a graph typically has heterogeneous dynamics (e.g., microscopic and macroscopic evolution patterns). As such, labeling a temporal graph is usually expensive and also requires background knowledge. To learn a good metric over temporal graphs, we propose a temporal graph metric learning framework, Temp-GFSM. With only a few labeled temporal graphs, Temp-GFSM outputs a good metric that can accurately classify different temporal graphs and be adapted to discover new subspaces for unseen classes. Each proposed component in Temp-GFSM answers the following questions: What patterns are evolving in a temporal graph? How to weigh these patterns to represent the characteristics of different temporal classes? And how to learn the metric with the guidance from only a few labels? Finally, the experimental results on real-world temporal graph classification tasks from various domains show the effectiveness of our Temp-GFSM.

KW - meta-learning

KW - metric learning

KW - temporal graph classification

UR - http://www.scopus.com/inward/record.url?scp=85136673460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85136673460&partnerID=8YFLogxK

U2 - 10.1145/3534678.3539313

DO - 10.1145/3534678.3539313

M3 - Conference contribution

AN - SCOPUS:85136673460

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 367

EP - 377

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 -