REVIEW 6 cited by
A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to capture structural, temporal, and contextual relationships in dynamic graphs simultaneously, leading to enhanced performance in various applications. As the demand for dynamic GNNs continues to grow, numerous models and frameworks have emerged to cater to different application needs. There is a pressing need for a comprehensive survey that evaluates the performance, strengths, and limitations of various approaches in this domain. This paper aims to fill this gap by offering a thorough comparative analysis and experimental evaluation of dynamic GNNs. It covers 81 dynamic GNN models with a novel taxonomy, 12 dynamic GNN training frameworks, and commonly used benchmarks. We also conduct experimental results from testing representative nine dynamic GNN models and three frameworks on six standard graph datasets. Evaluation metrics focus on convergence accuracy, training efficiency, and GPU memory usage, enabling a thorough comparison of performance across various models and frameworks. From the analysis and evaluation results, we identify key challenges and offer principles for future research to enhance the design of models and frameworks in the dynamic GNNs field.
Forward citations
Cited by 6 Pith papers
-
T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
T-GRAB, a set of three synthetic temporal-graph tasks, shows that no current TGNN reliably does counting, delayed cause-effect, or long-range spatio-temporal reasoning.
-
UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure
UniSAGE jointly models static and dynamic attributes in a single attribute graph and improves entity classification/regression over prior RDL and GNN baselines.
-
TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
TMetaNet uses Dowker Zigzag Persistence features to adapt the learning rate of dynamic GNNs per snapshot, improving dynamic link prediction and noise robustness on six benchmarks.
-
THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
THGFM couples shared-space and relation-partitioned attention branches with non-competitive gated fusion (TC-NGSF) and rotary temporal attention (RoTA), reporting +3.25% mean and +12.37% peak relative gains over a rei...
-
A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams
BADGNN adds a Lipschitz regularizer and an attention-temperature adjustment so that memory-based dynamic GNNs can train with large batches while keeping predictive accuracy.
-
Large Scalable Cross-Domain Graph Neural Networks for Personalized Notification at LinkedIn
At LinkedIn, a cross-domain GNN trained on a unified 8.6 billion-node graph with temporal modeling and multi-task learning reports a 0.62% CTR lift and a 0.10% WAU lift online.
Discussion (0). Sign in to comment.