CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
and Shenoy, Krishna V
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
CUTS-GPR performs numerically exact Gaussian process regression with near-linear scaling in training points N and low-order polynomial scaling in dimensions D by exploiting additive kernels on incomplete grids.
Graphical physics network integrated with DRL and intrinsic reward normalization lets an agent improve its intuitive physics model via intrinsic motivation in stationary and non-stationary 3D environments.
citing papers explorer
-
Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
-
Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids
CUTS-GPR performs numerically exact Gaussian process regression with near-linear scaling in training points N and low-order polynomial scaling in dimensions D by exploiting additive kernels on incomplete grids.
-
Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization
Graphical physics network integrated with DRL and intrinsic reward normalization lets an agent improve its intuitive physics model via intrinsic motivation in stationary and non-stationary 3D environments.