SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.12998 · 2026

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

Xikun Zhang, Jingchao Ni, Dongjin Song, Guiquan Sun

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
UConn-DSIS/DRIFT canonical 7 of 9
FunctionStatusWhere it lives
add_memory_grad Ran UConn-DSIS/DRIFT/Baselines/gss_model.py
pointer only (licence: NONE) · get_code("3980e3db08651b42")
compute_centers Ran UConn-DSIS/DRIFT/gaussian_utils.py
pointer only (licence: NONE) · get_code("0e4a15547d1dbd7b")
gaussian_task_weights Ran UConn-DSIS/DRIFT/gaussian_utils.py
pointer only (licence: NONE) · get_code("ea19b36bec167806")
get_grad_vector Ran UConn-DSIS/DRIFT/Baselines/gss_model.py
pointer only (licence: NONE) · get_code("db86aa783c4103d0")
normalized_mixing_entropy Ran UConn-DSIS/DRIFT/gaussian_utils.py
pointer only (licence: NONE) · get_code("9646c835abc89492")
task_changes Ran UConn-DSIS/DRIFT/metrics.py
pointer only (licence: NONE) · get_code("05137c22e8be0efc")
tf_metrics Ran UConn-DSIS/DRIFT/metrics.py
pointer only (licence: NONE) · get_code("5e131821209f5df2")
confusion_matrix Not yet run UConn-DSIS/DRIFT/metrics.py
pointer only (licence: NONE) · get_code("a115379e55454091")
get_model Not yet run UConn-DSIS/DRIFT/Backbones/model_factory.py
pointer only (licence: NONE) · get_code("a5ea5eeb095d63b9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.12998")
get_code_for_paper("2605.12998")
have("2605.12998")

Connect an agent — have() is free.