Foundation models pre-trained using self-supervised and weakly-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. Recently, the Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery (e.g., Sentinel-2) for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed countries not transferring well to data-scarce developing countries -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select six crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, the benefits of pre-training on OOD data are the most significant when only 10--100 ID training samples are used. Transfer learning and pre-training with OOD and limited ID data show promising applications, as many developing regions have scarce crop type labels. All harmonized datasets and experimental code are open-source and available for download.

This paper introduces Kolmogorov-Arnold Networks (KAN) as an enhancement to the traditional linear probing method in transfer learning. Linear probing, often applied to the final layer of pre-trained models, is limited by its inability to model complex relationships in data. To address this, we propose substituting the linear probing layer with KAN, which leverages spline-based representations to approximate intricate functions. In this study, we integrate KAN with a ResNet-50 model pre-trained on ImageNet and evaluate its performance on the CIFAR-10 dataset. We perform a systematic hyperparameter search, focusing on grid size and spline degree (k), to optimize KAN's flexibility and accuracy. Our results demonstrate that KAN consistently outperforms traditional linear probing, achieving significant improvements in accuracy and generalization across a range of configurations. These findings indicate that KAN offers a more powerful and adaptable alternative to conventional linear probing techniques in transfer learning.

Meta-learning has emerged as a powerful approach for leveraging knowledge from previous tasks to solve new tasks. The mainstream methods focus on training a well-generalized model initialization, which is then adapted to different tasks with limited data and updates. However, it pushes the model overfitting on the training tasks. Previous methods mainly attributed this to the lack of data and used augmentations to address this issue, but they were limited by sufficient training and effective augmentation strategies. In this work, we focus on the more fundamental ``learning to learn'' strategy of meta-learning to explore what causes errors and how to eliminate these errors without changing the environment. Specifically, we first rethink the algorithmic procedure of meta-learning from a ``learning'' lens. Through theoretical and empirical analyses, we find that (i) this paradigm faces the risk of both overfitting and underfitting and (ii) the model adapted to different tasks promote each other where the effect is stronger if the tasks are more similar. Based on this insight, we propose using task relations to calibrate the optimization process of meta-learning and propose a plug-and-play method called Task Relation Learner (TRLearner) to achieve this goal. Specifically, it first obtains task relation matrices from the extracted task-specific meta-data. Then, it uses the obtained matrices with relation-aware consistency regularization to guide optimization. Extensive theoretical and empirical analyses demonstrate the effectiveness of TRLearner.

This paper presents Adaptive Meta-Domain Transfer Learning (AMDTL), a novel methodology that combines principles of meta-learning with domain-specific adaptations to enhance the transferability of artificial intelligence models across diverse and unknown domains. AMDTL aims to address the main challenges of transfer learning, such as domain misalignment, negative transfer, and catastrophic forgetting, through a hybrid framework that emphasizes both generalization and contextual specialization. The framework integrates a meta-learner trained on a diverse distribution of tasks, adversarial training techniques for aligning domain feature distributions, and dynamic feature regulation mechanisms based on contextual domain embeddings. Experimental results on benchmark datasets demonstrate that AMDTL outperforms existing transfer learning methodologies in terms of accuracy, adaptation efficiency, and robustness. This research provides a solid theoretical and practical foundation for the application of AMDTL in various fields, opening new perspectives for the development of more adaptable and inclusive AI systems.

In multitask learning, conflicts between task gradients are a frequent issue degrading a model's training performance. This is commonly addressed by using the Gradient Projection algorithm PCGrad that often leads to faster convergence and improved performance metrics. In this work, we present a method to adapt this algorithm to simultaneously also perform task prioritization. Our approach differs from traditional task weighting performed by scaling task losses in that our weighting scheme applies only in cases where tasks are in conflict, but lets the training proceed unhindered otherwise. We replace task weighting factors by a probability distribution that determines which task gradients get projected in conflict cases. Our experiments on the nuScenes, CIFAR-100, and CelebA datasets confirm that our approach is a practical method for task weighting. Paired with multiple different task weighting schemes, we observe a significant improvement in the performance metrics of most tasks compared to Gradient Projection with uniform projection probabilities.

In the realm of dermatology, the complexity of diagnosing skin conditions manually necessitates the expertise of dermatologists. Accurate identification of various skin ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly in accurately diagnosing diseases across diverse skin tones, with a notable performance gap in darker skin. Additionally, the scarcity of publicly available, unbiased datasets hampers the development of inclusive AI diagnostic tools. To tackle the challenges in accurately predicting skin conditions across diverse skin tones, we employ a transfer-learning approach that capitalizes on the rich, transferable knowledge from various image domains. Our method integrates multiple pre-trained models from a wide range of sources, including general and specific medical images, to improve the robustness and inclusiveness of the skin condition predictions. We rigorously evaluated the effectiveness of these models using the Diverse Dermatology Images (DDI) dataset, which uniquely encompasses both underrepresented and common skin tones, making it an ideal benchmark for assessing our approach. Among all methods, Med-ViT emerged as the top performer due to its comprehensive feature representation learned from diverse image sources. To further enhance performance, we conducted domain adaptation using additional skin image datasets such as HAM10000. This adaptation significantly improved model performance across all models.

Multitask learning for improved scour detection: A dynamic wave tank study Simon M. Brealy, Aidan J. Hughes, Tina A. Dardeno, Lawrence A. Bull, Robin S. Mills, Nikolaos Dervilis, Keith Worden Bayesian hierarchical models help reduce uncertainty of foundation model parameters in populations of wind-turbines Reduced foundation parameter uncertainty aids detection of anomalies in dynamic behaviour during operation Future design of turbines may also be improved through reducing the likelihood and severity of fatigue damage Abstract Population-based structural health monitoring (PBSHM), aims to share information between members of a population. An offshore wind (OW) farm could be considered as a population of nominally-identical wind-turbine structures. However, benign variations exist among members, such as geometry, sea-bed conditions and temperature differences. These factors could influence structural properties and therefore the dynamic response, making it more difficult to detect structural problems via traditional SHM techniques. This paper explores the use of a Bayesian hierarchical model as a means of multitask learning, to infer foundation stiffness distribution parameters at both population and local levels. To do this, observations of natural frequency from populations of structures were first generated from both numerical and experimental models. These observations were then used in a partially-pooled Bayesian hierarchical model in tandem with surrogate FE models of the structures to infer foundation stiffness parameters.

In recent years, a number of papers have uncovered machine learning scaling laws--defined as empirical regularities that describe how the performance of a model increases as a function of scale, usually in parameter count and data (Hestness et al. 2017, Kaplan et al. 2020, Hoffmann et al. 2022). Hernandez et al. 2021 described scaling laws for transfer learning, showing how the transfer learning properties of models change as a function of model size. The primary result was that the degree of transfer--as measured by the amount of effective data transferred from one distribution to another--follows a simple power law in parameter count and fine-tuning data size. However, their analysis left much room for further exploration, as it only considered transfer learning from English to Python, and did not explore the relationship between the pre-training data size and the degree of downstream transfer learning. Scaling laws for transfer are important to study because they inform the degree to which progress in machine learning is bottlenecked by data for specific tasks. Consider that to achieve high performance on some tasks, one standard approach in the foundation model paradigm is to pre-train a model on a large, diverse distribution and then fine-tune it on a particular downstream task (Bommasani et al. 2022).

Domain Adaptation or Transfer Learning refer generally to the problem of harnessing data from a source distribution P to improve prediction performance w.r.t. to a target distribution Q for which some or no data is available. This problem has been researched over the last few decades with a recent resurgence in interest driven by modern applications that are often characterized by a scarcity of perfect target data. A fundamental question in the theory of domain adaptation (and variant problems on distribution shifts) is how to measure the relatedness between source P and target Q distributions. Importantly, desired measures of relatedness should not only tightly capture the predictive informationP has onQ, but have to be practically useful: that is, either the measure can be estimated from data to facilitate algorithmic design, or more generally, it should somehow admit adaptive procedures, i.e., procedures whose performance is adaptive to the a priori unknown level of relatedness between P and Q. Many notions have been proposed over the last few decades, starting with the seminal works of Mansour et al. [2009], Ben-David et al. [2010] on refinements of total-variation for domain adaptation in classification, to more recent proposals for domain adaptation in regression, e.g., Wasserstein distances Redko et al. [2017], Shen et al. [2018], or measures relating covariance structures across P and Q as in Mousavi Kalan et al. [2020], Zhang et al. [2022b], Ge et al. [2023]. These various notions of relatedness appear hard to compare at first glance, leading to a disparate theory of domain adaptation at present with no unified set of principles. Interestingly as we show, upon closer look at the existing literature--whether in classification or regression--it turns out that in fact, many seemingly distinct measures of relatedness proposed in domain adaptation actually implicitly bound the same fundamental quantities: we refer to these quantities as weak and strong moduli of transfer, and they roughly measure how fast the Q-risk of predictors decrease as their P -risk decreases. These moduli always yield as tight or tighter rates of transfer than many existing notions, while also admitting adaptive procedures in general settings, as shown via a reduction to the existence of certain confidence sets for the prediction problem at hand. These reductions, while of a theoretical nature, yield insights on general adaptive transfer approaches that are less tied to specific measures of relatedness between source P and target Q.

In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the performance of multiple tasks by facilitating the transfer of knowledge between their corresponding prompts in a multi-task setting. Our proposed approach decomposes the prompt for each target task into a combination of shared prompts (source prompts) and a task-specific prompt (private prompt). During training, the source prompts undergo fine-tuning and are integrated with the private prompt to drive the target prompt for each task. We present and compare multiple methods for combining source prompts to construct the target prompt, analyzing the roles of both source and private prompts within each method. We investigate their contributions to task performance and offer flexible, adjustable configurations based on these insights to optimize performance. Our empirical findings clearly showcase improvements in accuracy and robustness compared to the conventional practice of prompt tuning and related works. Notably, our results substantially outperform other methods in the field in few-shot settings, demonstrating superior performance in various tasks across GLUE benchmark, among other tasks. This achievement is attained with a significantly reduced amount of training data, making our method a promising one for few-shot settings.