Within-Network Classification in Temporal Graphs
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Within-Network Classification in Temporal Graphs. / Ryther, Christopher; Simonsen, Jakob.
Proceedings, 2018 IEEE International Conference on Data Mining Workshops (ICDMW). IEEE, 2018. p. 229-236.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Within-Network Classification in Temporal Graphs
AU - Ryther, Christopher
AU - Simonsen, Jakob
PY - 2018
Y1 - 2018
N2 - Recent results indicate that static graph features might not be adequate to solve challenges in graphs involving a temporal dimension. We analyze several classification problems using already established temporal metrics, and we propose label-sensitive and recency-sensitive variants of these metrics that capture labeling information and additional temporal patterns in the data. We test all new and old metrics, and a baseline based on a standard disease-spreading model, using tuned off-the-shelf classifiers on 9 datasets of varying size and usage domain. Our experiments indicate that usage of label-and recency-sensitive metrics on real-world data provides more accurate results than static approaches and approaches based on temporal metrics alone.
AB - Recent results indicate that static graph features might not be adequate to solve challenges in graphs involving a temporal dimension. We analyze several classification problems using already established temporal metrics, and we propose label-sensitive and recency-sensitive variants of these metrics that capture labeling information and additional temporal patterns in the data. We test all new and old metrics, and a baseline based on a standard disease-spreading model, using tuned off-the-shelf classifiers on 9 datasets of varying size and usage domain. Our experiments indicate that usage of label-and recency-sensitive metrics on real-world data provides more accurate results than static approaches and approaches based on temporal metrics alone.
U2 - 10.1109/ICDMW.2018.00041
DO - 10.1109/ICDMW.2018.00041
M3 - Article in proceedings
SP - 229
EP - 236
BT - Proceedings, 2018 IEEE International Conference on Data Mining Workshops (ICDMW)
PB - IEEE
T2 - 2018 IEEE International Conference on Data Mining Workshops (ICDMW)
Y2 - 17 November 2018 through 20 November 2018
ER -
ID: 239567139