CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
A Simple Neural Attentive Meta-Learner
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task. In response, recent work in meta-learning proposes training a meta-learner on a distribution of similar tasks, in the hopes of generalization to novel but related tasks by learning a high-level strategy that captures the essence of the problem it is asked to solve. However, many recent meta-learning approaches are extensively hand-designed, either using architectures specialized to a particular application, or hard-coding algorithmic components that constrain how the meta-learner solves the task. We propose a class of simple and generic meta-learner architectures that use a novel combination of temporal convolutions and soft attention; the former to aggregate information from past experience and the latter to pinpoint specific pieces of information. In the most extensive set of meta-learning experiments to date, we evaluate the resulting Simple Neural AttentIve Learner (or SNAIL) on several heavily-benchmarked tasks. On all tasks, in both supervised and reinforcement learning, SNAIL attains state-of-the-art performance by significant margins.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A novel complexity minimization meta-learning framework provably demonstrates that few-shot adaptation error decreases as meta-training data volume increases.
Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.
AbICL adapts antibody affinity ranking at test time by conditioning on labeled pairwise comparisons through a transformer context head trained with episodic meta-learning, achieving improved AUROC on the AbRank benchmark.
Placing one Hebbian fast-weight module after the final stage of Swin-Tiny achieves 96.2% accuracy on 5-way 1-shot Omniglot classification, outperforming the non-Hebbian baseline by 0.3 points.
citing papers explorer
-
CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations
CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
-
Provable Data Scaling Law for Meta Learning via Complexity Minimization
A novel complexity minimization meta-learning framework provably demonstrates that few-shot adaptation error decreases as meta-training data volume increases.
-
Solving Rubik's Cube with a Robot Hand
Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.
-
AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking
AbICL adapts antibody affinity ranking at test time by conditioning on labeled pairwise comparisons through a transformer context head trained with episodic meta-learning, achieving improved AUROC on the AbRank benchmark.
-
Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition
Placing one Hebbian fast-weight module after the final stage of Swin-Tiny achieves 96.2% accuracy on 5-way 1-shot Omniglot classification, outperforming the non-Hebbian baseline by 0.3 points.