PTCL: Pseudo-Label Temporal Curriculum Learning for Label-Limited Dynamic Graph

ICLR 2026 Conference Submission13582 Authors

Keywords: Dynamic Graph, Node classification, Pseudo-label, Curriculum Learning

Abstract:

Dynamic node classification is critical for modeling evolving systems like financial transactions and academic collaborations.
In such systems, dynamically capturing node information changes is critical for dynamic node classification, which usually requires all labels at every timestamp. However, it is difficult to collect all dynamic labels in real-world scenarios due to high annotation costs and label uncertainty (e.g., ambiguous or delayed labels in fraud detection). In contrast, final timestamp labels are easier to obtain as they rely on complete temporal patterns and are usually maintained as a unique label for each user in many open platforms, without tracking the history data. To bridge this gap, we propose a pioneering method PTCL (Pseudo-label Temporal Curriculum Learning), combining the variational EM framework with a novel Temporal Curriculum Learning strategy to effectively leverage both final timestamp labels and pseudo-labels. We also contribute a new academic dataset (CoOAG), capturing long-range research interest in dynamic graph. Experiments across real-world scenarios demonstrate PTCL’s consistent superiority over other methods adapted to this task. Beyond methodology, we propose a unified framework FLiD (Framework for Label-Limited Dynamic Node Classification), consisting of a complete preparation workflow, training pipeline, and evaluation standards, and supporting various models and datasets. Code details can be found in supplementary materials.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 13582