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.
Therefore, this can be viewed as the lower bound on the continual learning performance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.