Back to papers
Understanding Evolving Graph Structures for Large Discrete-Time Dynamic Graph Representation
Summary: UnderGS targets DTDG representation learning by replacing per-snapshot O(T|V|^2) adjacency storage with a GPU-resident temporal-cohesive neighbor store, maintaining only influential temporal neighbors via a temporal influence score. Lightweight, model-agnostic pipeline (MPNN/non-MPNN) with late-snapshot gradient aggregation; up to 9x faster, +31% accuracy.
(summarized by gpt-5.4-mini on Apr 12 2026)
- Paper ID
- 14379
- Venue
- VLDB
- Year
- 2026
- Pagerank
- 4.1905499e-05
- Overall Rank
- 10,334 | 28.18%
- DOI
-
10.14778/3796195.3796201
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 271 |
AliGraph: A Comprehensive Graph Neural Network Platform |
2019 |
VLDB |
0.00029565193 |
| 1,388 |
TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs |
2022 |
VLDB |
0.00012249747 |
| 3,715 |
Zebra: When Temporal Graph Neural Networks Meet Temporal Personalized PageRank |
2023 |
VLDB |
6.8176818e-05 |
| 5,146 |
Efficient Tree-SVD for Subset Node Embedding over Large Dynamic Graphs |
2023 |
SIGMOD |
5.6589364e-05 |
| 5,356 |
NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams |
2024 |
VLDB |
5.5514335e-05 |
| 5,452 |
Decoupled Graph Neural Networks for Large Dynamic Graphs |
2023 |
VLDB |
5.4972958e-05 |
| 5,485 |
ETC: Efficient Training of Temporal Graph Neural Networks over Large-scale Dynamic Graphs |
2024 |
VLDB |
5.4817019e-05 |
| 5,721 |
DynaHB: A Communication-Avoiding Asynchronous Distributed Framework with Hybrid Batches for Dynamic GNN Training |
2024 |
VLDB |
5.3538607e-05 |
| 6,479 |
EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs |
2023 |
SIGMOD |
5.0405101e-05 |
| 7,014 |
SIMPLE: Efficient Temporal Graph Neural Network Training at Scale with Dynamic Data Placement |
2024 |
SIGMOD |
4.8570865e-05 |
| 7,750 |
GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs |
2024 |
VLDB |
4.6565447e-05 |
| 8,459 |
D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks |
2024 |
VLDB |
4.5008938e-05 |
| 8,507 |
Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense |
2024 |
VLDB |
4.4909322e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 5,485 |
ETC: Efficient Training of Temporal Graph Neural Networks over Large-scale Dynamic Graphs |
2024 |
VLDB |
5.4817019e-05 |
| 7,014 |
SIMPLE: Efficient Temporal Graph Neural Network Training at Scale with Dynamic Data Placement |
2024 |
SIGMOD |
4.8570865e-05 |
| 10,889 |
Efficient Graph Embedding Generation and Update for Large-Scale Temporal Graph |
2025 |
VLDB |
4.1905499e-05 |
| 6,479 |
EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs |
2023 |
SIGMOD |
5.0405101e-05 |
| 5,016 |
DGC: Training Dynamic Graphs with Spatio-Temporal Non-Uniformity using Graph Partitioning by Chunks |
2023 |
SIGMOD |
5.7512359e-05 |
| 1,388 |
TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs |
2022 |
VLDB |
0.00012249747 |
| 9,277 |
Temporal SIR-GN: Efficient and Effective Structural Representation Learning for Temporal Graphs |
2023 |
VLDB |
4.3610659e-05 |
| 10,267 |
FlareDTDG: Harnessing Temporal Recency for Scalable Discrete-Time Dynamic Graph Training |
2026 |
VLDB |
4.1905499e-05 |
| 5,452 |
Decoupled Graph Neural Networks for Large Dynamic Graphs |
2023 |
VLDB |
5.4972958e-05 |
| 10,891 |
Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours |
2025 |
VLDB |
4.1905499e-05 |