Invariant Gradient Alignment uses Logical Isomer Sets and a Continuous Gradient Conflict Mask to tighten OOD generalization bounds and boost empirical performance over ERM in reasoning distillation.
Gradient matching for domain generalization
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
verdicts
UNVERDICTED 8representative citing papers
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
Evaluates four distribution shifts in sensor-based HAR, finds diversity shifts dominate, and shows 28 DG methods only marginally beat ERM while releasing open benchmarks.
FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.
Merged bilingual CS-ASR models show only modest generalization to unseen language pairs, indicating limited transfer of code-switching capabilities.
An empirical Bayes variational inference method learns environment-robust latent variables from multi-environment data for improved prediction in unseen environments.
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
Causal Fine-Tuning decomposes BERT representations into causal and spurious parts via SCM inductive bias to improve robustness under latent confounded shifts in text classification.
citing papers explorer
-
Invariant Gradient Alignment for Robust Reasoning Distillation
Invariant Gradient Alignment uses Logical Isomer Sets and a Continuous Gradient Conflict Mask to tighten OOD generalization bounds and boost empirical performance over ERM in reasoning distillation.
-
Continual Learning of Domain-Invariant Representations
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
-
Assessing Distribution Shift in Human Activity Recognition for Domain Generalization
Evaluates four distribution shifts in sensor-based HAR, finds diversity shifts dominate, and shows 28 DG methods only marginally beat ERM while releasing open benchmarks.
-
Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.
-
Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs
Merged bilingual CS-ASR models show only modest generalization to unseen language pairs, indicating limited transfer of code-switching capabilities.
-
Environment-Robust Representation Learning with Empirical Bayes
An empirical Bayes variational inference method learns environment-robust latent variables from multi-environment data for improved prediction in unseen environments.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
-
Causal Fine-Tuning under Latent Confounded Shift
Causal Fine-Tuning decomposes BERT representations into causal and spurious parts via SCM inductive bias to improve robustness under latent confounded shifts in text classification.