Self-Supervised Deep Metric Learning for Pointsets

Arsomngern, Pattaramanee; Long, Cheng; Suwajanakorn, Supasorn; Nutanong, Sarana

doi:10.1109/icde51399.2021.00219

Cited by 8 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, self-supervised learning (SSL) becomes a promising solution to enhance the representation capability of neural networks, so as to address the limitation of high reliance on sufficient labeled data for model training [1], [26]. The effectiveness of SSL has been demonstrated in various domains, such as computer vision [18], nature language understanding [6], graph representation learning [34].…”

Section: Self-supervised Learningmentioning

confidence: 99%

Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction

Li,

Huang,

Xia

et al. 2022

Preprint

View full text Add to dashboard Cite

Crime has become a major concern in many cities, which calls for the rising demand for timely predicting citywide crime occurrence. Accurate crime prediction results are vital for the beforehand decision-making of government to alleviate the increasing concern about the public safety. While many efforts have been devoted to proposing various spatial-temporal forecasting techniques to explore dependence across locations and time periods, most of them follow a supervised learning manner, which limits their spatial-temporal representation ability on sparse crime data. Inspired by the recent success in self-supervised learning, this work proposes a Spatial-Temporal Self-Supervised Hypergraph Learning framework (ST-HSL) to tackle the label scarcity issue in crime prediction. Specifically, we propose the cross-region hypergraph structure learning to encode region-wise crime dependency under the entire urban space. Furthermore, we design the dual-stage self-supervised learning paradigm, to not only jointly capture local-and global-level spatial-temporal crime patterns, but also supplement the sparse crime representation by augmenting region self-discrimination. We perform extensive experiments on two real-life crime datasets. Evaluation results show that our ST-HSL significantly outperforms state-of-theart baselines. Further analysis provides insights into the superiority of our ST-HSL method in the representation of spatialtemporal crime patterns. The implementation code is available at https://github.com/LZH-YS1998/STHSL.

show abstract