SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
Proceedings of the 20th International conference on Machine learning (ICML-03) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
STEPS reformulates test-time adaptation for time series forecasting as a Dirichlet boundary value problem on a temporal manifold and solves for smooth error corrections, yielding 26.82% average relative MSE reduction over zero-shot baselines.
citing papers explorer
-
SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
-
STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting
STEPS reformulates test-time adaptation for time series forecasting as a Dirichlet boundary value problem on a temporal manifold and solves for smooth error corrections, yielding 26.82% average relative MSE reduction over zero-shot baselines.