DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts

Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typically adopt a task-based formulation, where the data stream is partitioned into a sequence of discrete tasks with pre-defined boundaries. However, such assumptions rarely hold in real-world environments, where data distributions evolve continuously and task identity is often unavailable. To better reflect realistic non-stationary environments, we revisit continual graph learning from a task-free perspective. We propose a unified formulation that models the data stream as a time-varying mixture of latent task distributions, enabling continuous modeling of distribution drift. Based on this formulation, we construct \emph{DRIFT}, a benchmark that spans a spectrum of transition dynamics ranging from hard task switches to smooth distributional drift through a Gaussian parameterization. We evaluate representative continual learning methods under this task-free setting and observe substantial performance degradation compared to traditional task-based protocols. Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams. This work highlights the importance of studying continual graph learning under realistic non-stationary conditions and provides a benchmark for future research in this direction. Our code is available at https://github.com/UConn-DSIS/DRIFT.

Towards Heterogeneous Continual Graph Learning via Meta-knowledge Distillation

Machine learning on heterogeneous graphs has experienced rapid advancement in recent years, driven by the inherently heterogeneous nature of real-world data. However, existing studies typically assume the graphs to be static, while real-world graphs are continuously expanding. This dynamic nature requires models to adapt to new data while preserving existing knowledge. To this end, this work addresses the challenge of continual learning on heterogeneous graphs by introducing the Meta-learning based Knowledge Distillation framework (MKD), designed to mitigate catastrophic forgetting in evolving heterogeneous graph structures. MKD combines rapid task adaptation through meta-learning on limited samples with knowledge distillation to achieve an optimal balance between incorporating new information and maintaining existing knowledge. To improve the efficiency and effectiveness of sample selection, MKD incorporates a novel sampling strategy that selects a small number of target-type nodes based on node diversity and maintains fixed-size buffers for other types. The strategy retrieves first-order neighbors along metapaths and selects important neighbors based on their structural relevance, enabling the sampled subgraphs to retain key topological and semantic information. In addition, MKD introduces a semantic-level distillation module that aligns the attention distributions over different metapaths between teacher and student models, encouraging semantic consistency beyond the logit level. Comprehensive evaluations across three benchmark datasets validate MKD's effectiveness in handling continual learning scenarios on expanding heterogeneous graphs.