From random-walks to graph-sprints: a low-latency node embedding framework on continuous-time dynamic graphs

• Type: Article in International Conference Proceedings Book
• Date: 2023

Authors

Eddin, AN (Author) Other; Bono, J (Author) Other; Aparício, D (Author) Other; Ferreira, H (Author) Other; Ascensao, J (Author) Other; Pedro Ribeiro (Author) FCUP; Bizarro, P (Author) Other

Conference proceedings International

Title: PROCEEDINGS OF THE 4TH ACM INTERNATIONAL CONFERENCE ON AI IN FINANCE, ICAIF 2023

Pages: 176-184

4th ACM International Conference on AI in Finance (ICAIF)

Brooklyn, NY, NOV 27-29, 2023

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 2 Citations

Other information

Authenticus ID: P-00Z-25Z

DOI: 10.1145/3604237.3626842

Abstract (EN): Many real-world datasets have an underlying dynamic graph structure, where entities and their interactions evolve over time. Machine learning models should consider these dynamics in order to harness their full potential in downstream tasks. Previous approaches for graph representation learning have focused on either sampling khop neighborhoods, akin to breadth-first search, or random walks, akin to depth-first search. However, these methods are computationally expensive and unsuitable for real-time, low-latency inference on dynamic graphs. To overcome these limitations, we propose graph-sprints a general purpose feature extraction framework for continuous-time-dynamic-graphs (CTDGs) that has low latency and is competitive with state-of-the-art, higher latency models. To achieve this, a streaming, low latency approximation to the random-walk based features is proposed. In our framework, time-aware node embeddings summarizing multi-hop information are computed using only single-hop operations on the incoming edges. We evaluate our proposed approach on three open-source datasets and two in-house datasets, and compare with three state-of-the-art algorithms (TGN-attn, TGN-ID, Jodie). We demonstrate that our graph-sprints features, combined with a machine learning classifier, achieve competitive performance (outperforming all baselines for the node classification tasks in five datasets). Simultaneously, graphsprints significantly reduce inference latencies, achieving close to an order of magnitude speed-up in our experimental setting.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 9