FDGNN: Fully Dynamic Graph Neural Network

Moallemy-Oureh, Alice; Beddar-Wiesing, Silvia; Nather, Rüdiger; Thomas, Josephine Maria

doi:10.48550/arxiv.2206.03469

Cited by 2 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find that the dynamic GNN models [20,27,28,34,45,51,57,63,79] designed for graph streams adopt the traditional batched training mode to learn parameters. Each batch consists of a sequence of historical events {𝑒 [1], 𝑒 [2], .…”

Section: Dynamic Gnn Training Abstractionmentioning

confidence: 99%

“…However, real-world graphs are inherently dynamic and evolving over time. Recently, many dynamic GNN models [20,27,28,34,45,51,57,63,79] are emerged as a promising method for learning from dynamic graphs. These models capture both the spatial and temporal information, which makes them outperform traditional GNNs in real-time applications, such as real-time fraud detection [57], real-time recommendation [20], and many other tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

Chen,

Gao,

Zhang

et al. 2023

Proc. VLDB Endow.

View full text Add to dashboard Cite

Existing Graph Neural Network (GNN) training frameworks have been designed to help developers easily create performant GNN implementations. However, most existing GNN frameworks assume that the input graphs are static, but ignore that most real-world graphs are constantly evolving. Though many dynamic GNN models have emerged to learn from evolving graphs, the training process of these dynamic GNNs is dramatically different from traditional GNNs in that it captures both the spatial and temporal dependencies of graph updates. This poses new challenges for designing dynamic GNN training frameworks. First, the traditional batched training method fails to capture real-time structural evolution information. Second, the time-dependent nature makes parallel training hard to design. Third, it lacks system supports for users to efficiently implement dynamic GNNs. In this paper, we present NeutronStream, a framework for training dynamic GNN models. NeutronStream abstracts the input dynamic graph into a chronologically updated stream of events and processes the stream with an optimized sliding window to incrementally capture the spatial-temporal dependencies of events. Furthermore, NeutronStream provides a parallel execution engine to tackle the sequential event processing challenge to achieve high performance. NeutronStream also integrates a built-in graph storage structure that supports dynamic updates and provides a set of easy-to-use APIs that allow users to express their dynamic GNNs. Our experimental results demonstrate that, compared to state-of-the-art dynamic GNN implementations, NeutronStream achieves speedups ranging from 1.48X to 5.87X and an average accuracy improvement of 3.97%.

show abstract

Section: Dynamic Gnn Training Abstractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

Chen,

Gao,

Zhang

et al. 2023

Proc. VLDB Endow.

View full text Add to dashboard Cite

show abstract

“…Concurrently, another investigative work [13] harnesses the Hawkes process, emphasizing the modeling of dynamic link additions, with a concentrated focus on their temporal evolution. Conversely, FDGNN [14] introduces an avant-garde framework dedicated to node and edge embeddings. This method showcases proficiency in capturing Temporal Point Processes, hinting at the potential for devising encodings symbiotic with incoming graph events.…”

Section: Related Workmentioning

confidence: 99%

Entropy-Aware Time-Varying Graph Neural Networks with Generalized Temporal Hawkes Process: Dynamic Link Prediction in the Presence of Node Addition and Deletion

Najafi,

Parsaeefard,

Leon-Garcia

2023

MAKE

View full text Add to dashboard Cite

This paper addresses the problem of learning temporal graph representations, which capture the changing nature of complex evolving networks. Existing approaches mainly focus on adding new nodes and edges to capture dynamic graph structures. However, to achieve more accurate representation of graph evolution, we consider both the addition and deletion of nodes and edges as events. These events occur at irregular time scales and are modeled using temporal point processes. Our goal is to learn the conditional intensity function of the temporal point process to investigate the influence of deletion events on node representation learning for link-level prediction. We incorporate network entropy, a measure of node and edge significance, to capture the effect of node deletion and edge removal in our framework. Additionally, we leveraged the characteristics of a generalized temporal Hawkes process, which considers the inhibitory effects of events where past occurrences can reduce future intensity. This framework enables dynamic representation learning by effectively modeling both addition and deletion events in the temporal graph. To evaluate our approach, we utilize autonomous system graphs, a family of inhomogeneous sparse graphs with instances of node and edge additions and deletions, in a link prediction task. By integrating these enhancements into our framework, we improve the accuracy of dynamic link prediction and enable better understanding of the dynamic evolution of complex networks.

show abstract

FDGNN: Fully Dynamic Graph Neural Network

Cited by 2 publications

References 3 publications

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

Entropy-Aware Time-Varying Graph Neural Networks with Generalized Temporal Hawkes Process: Dynamic Link Prediction in the Presence of Node Addition and Deletion

Contact Info

Product

Resources

About