P |
Beddar-Wiesing, S.
(2022):
Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs.
In: ACM/SIGAPP Symposium on Applied Computing (SAC),
[Volltext]
[Kurzfassung] [BibTeX][Endnote]
Graphs have recently become more popular for modeling real-world well as theoretical problems, and several Machine Learning algorithms r learning on them have developed. For graphs that change er time, however, research is still at an early stage. This article proposes framework DynHeatmaP that generates a constant-size aph sequence representation of graphs whose structure changes er time (structural-dynamic, SDG) in linear time. The framework es a representation of additions and deletions of nodes and edges vents) to perform dynamic graph pooling. Our algorithm translates e dynamic changes of the nodes and edges to a heatmap presentation of the current node activity, regarding additions and letions in the neighborhood, respectively. The created activity atmap is utilized as probabilities of the nodes to be sampled in the bsequent pooling step. In addition, the neighborhood of selected des has been sampled such that the ratio of additions and deletions represented accordingly. The obtained downsampled graph quence can then be used representatively as input to a GNN for arning on the original stream. Focussing on the active regions a graph, the fast pooling process can reduce the training time gnificantly and addresses the problem of unbalanced datasets in al-world applications modeled as sparse graphs.
@inproceedings{beddarwiesing2022student,
author = {Beddar-Wiesing, Silvia},
title = {Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs},
booktitle = {ACM/SIGAPP Symposium on Applied Computing (SAC)},
publisher = {ACM},
year = {2022},
pages = {604--609},
url = {https://dl.acm.org/doi/abs/10.1145/3477314.3506969},
doi = {10.1145/3477314.3506969},
keywords = {imported, itegpub, isac-www},
abstract = {Graphs have recently become more popular for modeling real-world
well as theoretical problems, and several Machine Learning algorithms r learning on them have developed. For graphs that change er time, however, research is still at an early stage. This article proposes framework DynHeatmaP that generates a constant-size aph sequence representation of graphs whose structure changes er time (structural-dynamic, SDG) in linear time. The framework es a representation of additions and deletions of nodes and edges vents) to perform dynamic graph pooling. Our algorithm translates e dynamic changes of the nodes and edges to a heatmap presentation of the current node activity, regarding additions and letions in the neighborhood, respectively. The created activity atmap is utilized as probabilities of the nodes to be sampled in the bsequent pooling step. In addition, the neighborhood of selected des has been sampled such that the ratio of additions and deletions represented accordingly. The obtained downsampled graph quence can then be used representatively as input to a GNN for arning on the original stream. Focussing on the active regions a graph, the fast pooling process can reduce the training time gnificantly and addresses the problem of unbalanced datasets in al-world applications modeled as sparse graphs.} }
%0 = inproceedings
%A = Beddar-Wiesing, Silvia
%B = ACM/SIGAPP Symposium on Applied Computing (SAC)
%D = 2022
%I = ACM
%T = Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs
%U = https://dl.acm.org/doi/abs/10.1145/3477314.3506969
|