Informed Meta-Learning
In noisy and low-data regimes prevalent in real-world applications, a key challenge of machine learning lies in effectively incorporating inductive biases that promote data efficiency and robustness. Meta-learning and informed ML stand out as two approaches for incorporating prior knowledge into ML pipelines. While the former relies on a purely data-driven source of priors, the latter is guided by prior domain knowledge. In this paper, we formalise a hybrid paradigm, informed meta-learning, facilitating the incorporation of priors from unstructured knowledge representations, such as natural language; thus, unlocking complementarity in cross-task knowledge sharing of humans and machines. We establish the foundational components of informed meta-learning and present a concrete instantiation of this framework--the Informed Neural Process. Through a series of experiments, we demonstrate the potential benefits of informed meta-learning in improving data efficiency, robustness to observational noise and task distribution shifts.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningSimilar Papers 제목 키워드 기반
Hybrid physics-informed metabolic cybergenetics: process rates augmented with machine-learning surrogates informed by flux balance analysis
Metabolic cybergenetics is a promising concept that interfaces gene expression and cellular metabolism with computers for real-time dynamic metabolic control. The focus is on control at the transcriptional level, serving…
Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting
Spatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remai…
Time SeriesTime Series ForecastingQ-Net: Query-Informed Few-Shot Medical Image Segmentation
Deep learning has achieved tremendous success in computer vision, while medical image segmentation (MIS) remains a challenge, due to the scarcity of data annotations. Meta-learning techniques for few-shot segmentation (M…
Anomaly DetectionImage SegmentationMedical Image SegmentationMeta-Learning+1Meta-learning Loss Functions of Parametric Partial Differential Equations Using Physics-Informed Neural Networks
This paper proposes a new way to learn Physics-Informed Neural Network loss functions using Generalized Additive Models. We apply our method by meta-learning parametric partial differential equations, PDEs, on Burger's a…
Additive modelsMeta-LearningMetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy
Miniaturized endoscopy has advanced accurate visual perception within the human body. Prevailing research remains limited to conventional cameras employing convex lenses, where the physical constraints with millimetre-sc…