DRIFT is a benchmark modeling continual graph data streams as time-varying mixtures of latent task distributions via Gaussian parameterization, revealing substantial performance degradation in existing continual learning methods under task-free continuous drift.
Continual learning on graphs: Challenges, solutions, and opportunities.arXiv preprint arXiv:2402.11565, 2024
5 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
5
Pith papers citing it
5
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
UFO combines flow-based generative replay with instance-level reliability scoring to handle both catastrophic forgetting and catastrophic remembering from noisy supervision in evolving graphs, outperforming baselines on four datasets.
A BART-GraphSAGE hybrid achieves ROC-AUC 67.40 on one RelBench task, competitive with LightGBM but still behind specialized relational deep learning and foundation models.
SA-HGNN with contrastive learning improves power outage prediction by modeling spatial effects of extreme weather on infrastructure across multiple utility territories.
G2LoRA proposes category-aware gradient projection and magnitude modulation within a unified graph-text alignment objective to mitigate interference and promote transfer in continual learning on text-attributed graphs.
citing papers explorer
-
DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
DRIFT is a benchmark modeling continual graph data streams as time-varying mixtures of latent task distributions via Gaussian parameterization, revealing substantial performance degradation in existing continual learning methods under task-free continuous drift.
-
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
UFO combines flow-based generative replay with instance-level reliability scoring to handle both catastrophic forgetting and catastrophic remembering from noisy supervision in evolving graphs, outperforming baselines on four datasets.
-
Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
A BART-GraphSAGE hybrid achieves ROC-AUC 67.40 on one RelBench task, competitive with LightGBM but still behind specialized relational deep learning and foundation models.
-
Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning
SA-HGNN with contrastive learning improves power outage prediction by modeling spatial effects of extreme weather on infrastructure across multiple utility territories.
-
G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
G2LoRA proposes category-aware gradient projection and magnitude modulation within a unified graph-text alignment objective to mitigate interference and promote transfer in continual learning on text-attributed graphs.