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

by   Ahmad Naser Eddin, et al.

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 k-hop 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, graph-sprints significantly reduce inference latencies, achieving close to an order of magnitude speed-up in our experimental setting.


page 1

page 2

page 3

page 4


Efficient Representation Learning Using Random Walks for Dynamic graphs

An important part of many machine learning workflows on graphs is vertex...

Space-Efficient Random Walks on Streaming Graphs

Graphs in many applications, such as social networks and IoT, are inhere...

APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding

Limited by the time complexity of querying k-hop neighbors in a graph da...

Graph topological property recovery with heat and wave dynamics-based features on graphs

In this paper, we propose Graph Differential Equation Network (GDeNet), ...

Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach

Non-Intrusive Load Monitoring (NILM) enables the disaggregation of the g...

Two-Hop Walks Indicate PageRank Order

This paper shows that pairwise PageRank orders emerge from two-hop walks...

Network navigation using Page Rank random walks

We introduce a formalism based on a continuous time approximation, to st...

Please sign up or login with your details

Forgot password? Click here to reset