The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. In this work, we introduce the Harmony Multi-Task Decision Transformer (HarmoDT), a novel solution designed to identify an optimal harmony subspace of parameters for each task. We approach this as a bi-level optimization problem, employing a meta-learning framework that leverages gradient-based techniques. The upper level of this framework is dedicated to learning a task-specific mask that delineates the harmony subspace, while the inner level focuses on updating parameters to enhance the overall performance of the unified policy. Empirical evaluations on a series of benchmarks demonstrate the superiority of HarmoDT, verifying the effectiveness of our approach.
Advances in Deep Learning bring further investigation into credibility and robustness, especially for safety-critical engineering applications such as the nuclear industry. The key challenges include the availability of data set (often scarce and sparse) and insufficient consideration of the uncertainty in the data, model, and prediction. This paper therefore presents a meta-learning based approach that is both uncertainty- and prior knowledge-informed, aiming at trustful predictions of material properties for the nuclear reactor design. It is suited for robust learning under limited data. Uncertainty has been accounted for where a distribution of predictor functions are produced for extrapolation. Results suggest it achieves superior performance than existing empirical methods in rupture life prediction, a case which is typically under a small data regime. While demonstrated herein with rupture properties, this learning approach is transferable to solve similar problems of data scarcity across the nuclear industry. It is of great importance to boosting the AI analytics in the nuclear industry by proving the applicability and robustness while providing tools that can be trusted.
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience. However, the aspect of constraint violations has not been adequately addressed in the existing works, making their application restricted in real-world settings. In this paper, we study the problem of meta-safe reinforcement learning (Meta-SRL) through the CMDP-within-online framework to establish the first provable guarantees in this important setting. We obtain task-averaged regret bounds for the reward maximization (optimality gap) and constraint violations using gradient-based meta-learning and show that the task-averaged optimality gap and constraint satisfaction improve with task-similarity in a static environment or task-relatedness in a dynamic environment. Several technical challenges arise when making this framework practical. To this end, we propose a meta-algorithm that performs inexact online learning on the upper bounds of within-task optimality gap and constraint violations estimated by off-policy stationary distribution corrections. Furthermore, we enable the learning rates to be adapted for every task and extend our approach to settings with a competing dynamically changing oracle. Finally, experiments are conducted to demonstrate the effectiveness of our approach.
Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen tasks. Current methods often overlook the heterogeneity among pre-trained models, which leads to performance degradation due to task conflicts. In this paper, we empirically and theoretically identify and analyze the model heterogeneity in DFML. We find that model heterogeneity introduces a heterogeneity-homogeneity trade-off, where homogeneous models reduce task conflicts but also increase the overfitting risk. Balancing this trade-off is crucial for learning shared representations across tasks. Based on our findings, we propose Task Groupings Regularization that benefits from model heterogeneity by grouping and aligning conflicting tasks. Specifically, we embed pre-trained models into a task space to compute dissimilarity, and group heterogeneous models together based on this measure. Then, we introduce implicit gradient regularization within each group to mitigate potential conflicts. By encouraging a gradient direction suitable for all tasks, the meta-model captures shared representations that generalize across tasks. Comprehensive experiments showcase the superiority of our approach in multiple benchmarks, effectively tackling the model heterogeneity in challenging multi-domain and multi-architecture scenarios.
Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control systems. In this paper, we study the problem of using meta-learning to deal with uncertainty and heterogeneity in ergodic linear quadratic regulators. We integrate the zeroth-order optimization technique with a typical meta-learning method, proposing an algorithm that omits the estimation of policy Hessian, which applies to tasks of learning a set of heterogeneous but similar linear dynamic systems. The induced meta-objective function inherits important properties of the original cost function when the set of linear dynamic systems are meta-learnable, allowing the algorithm to optimize over a learnable landscape without projection onto the feasible set. We provide a convergence result for the exact gradient descent process by analyzing the boundedness and smoothness of the gradient for the meta-objective, which justify the proposed algorithm with gradient estimation error being small. We also provide a numerical example to corroborate this perspective.
Recently, few-shot molecular property prediction (FSMPP) has garnered increasing attention. Despite impressive breakthroughs achieved by existing methods, they often overlook the inherent many-to-many relationships between molecules and properties, which limits their performance. For instance, similar substructures of molecules can inspire the exploration of new compounds. Additionally, the relationships between properties can be quantified, with high-related properties providing more information in exploring the target property than those low-related. To this end, this paper proposes a novel meta-learning FSMPP framework (KRGTS), which comprises the Knowledge-enhanced Relation Graph module and the Task Sampling module. The knowledge-enhanced relation graph module constructs the molecule-property multi-relation graph (MPMRG) to capture the many-to-many relationships between molecules and properties. The task sampling module includes a meta-training task sampler and an auxiliary task sampler, responsible for scheduling the meta-training process and sampling high-related auxiliary tasks, respectively, thereby achieving efficient meta-knowledge learning and reducing noise introduction. Empirically, extensive experiments on five datasets demonstrate the superiority of KRGTS over a variety of state-of-the-art methods. The code is available in https://github.com/Vencent-Won/KRGTS-public.
Recent advances in multimodal foundation models have set new standards in few-shot anomaly detection. This paper explores whether high-quality visual features alone are sufficient to rival existing state-of-the-art vision-language models. We affirm this by adapting DINOv2 for one-shot and few-shot anomaly detection, with a focus on industrial applications. We show that this approach does not only rival existing techniques but can even outmatch them in many settings. Our proposed vision-only approach, AnomalyDINO, is based on patch similarities and enables both image-level anomaly prediction and pixel-level anomaly segmentation. The approach is methodologically simple and training-free and, thus, does not require any additional data for fine-tuning or meta-learning. Despite its simplicity, AnomalyDINO achieves state-of-the-art results in one- and few-shot anomaly detection (e.g., pushing the one-shot performance on MVTec-AD from an AUROC of 93.1% to 96.6%). The reduced overhead, coupled with its outstanding few-shot performance, makes AnomalyDINO a strong candidate for fast deployment, e.g., in industrial contexts.
Unmanned aerial vehicles (UAVs) with multiple antennas have recently been explored to improve capacity in wireless networks. However, the strict energy constraint of UAVs, given their simultaneous flying and communication tasks, renders the exploration of energy-efficient multi-antenna techniques indispensable for UAVs. Meanwhile, lens antenna subarray (LAS) emerges as a promising energy-efficient solution that has not been previously harnessed for this purpose. In this paper, we propose a LAS-aided multi-antenna UAV to serve ground users in the downlink transmission of the terahertz (THz) band, utilizing rate splitting multiple access (RSMA) for effective beam division multiplexing. We formulate an optimization problem of maximizing the total system spectral efficiency (SE). This involves optimizing the UAV's transmit beamforming and the common rate of RSMA. By recasting the optimization problem into a Markov decision process (MDP), we propose a deep deterministic policy gradient (DDPG)-based resource allocation mechanism tailored to capture problem dynamics and optimize its variables. Moreover, given the UAV's frequent mobility and consequential system reconfigurations, we fortify the trained DDPG model with a meta-learning strategy, enhancing its adaptability to system variations. Numerically, more than 20\% energy efficiency gain is achieved by our proposed LAS-aided multi-antenna UAV equipped with 4 lenses, compared to a single-lens UAV. Simulations also demonstrate that at a signal-to-noise (SNR) of 10 dB, the incorporation of RSMA results in a 22\% SE enhancement over conventional orthogonal beam division multiple access. Furthermore, the overall system SE improves by 27\%, when meta-learning is employed for fine-tuning the conventional DDPG method in literature.
This paper centers around a multiple-input-multiple-output (MIMO) visible light communication (VLC) system, where an unmanned aerial vehicle (UAV) benefits from a light emitting diode (LED) array to serve photo-diode (PD)-equipped users for illumination and communication simultaneously. Concerning the battery limitation of the UAV and considerable energy consumption of the LED array, a hybrid dimming control scheme is devised at the UAV that effectively controls the number of glared LEDs and thereby mitigates the overall energy consumption. To assess the performance of this system, a radio resource allocation problem is accordingly formulated for jointly optimizing the motion trajectory, transmit beamforming and LED selection at the UAV, assuming that channel state information (CSI) is partially available. By reformulating the optimization problem in Markov decision process (MDP) form, we propose a soft actor-critic (SAC) mechanism that captures the dynamics of the problem and optimizes its parameters. Additionally, regarding the high mobility of the UAV and thus remarkable rearrangement of the system, we enhance the trained SAC model by integrating a meta-learning strategy that enables more adaptation to system variations. By defining energy efficiency as a trade-off between the data rate and power consumption, simulations verify that upgrading a single-LED UAV by an array of 10 LEDs, exhibits 47% and 34% improvements in data rate and energy efficiency, albeit at the expense of 8% more power consumption.
The reason for Meta Overfitting can be attributed to two factors: Mutual Non-exclusivity and the Lack of diversity, consequent to which a single global function can fit the support set data of all the meta-training tasks and fail to generalize to new unseen tasks. This issue is evidenced by low error rates on the meta-training tasks, but high error rates on new tasks. However, there can be a number of novel solutions to this problem keeping in mind any of the two objectives to be attained, i.e. to increase diversity in the tasks and to reduce the confidence of the model for some of the tasks. In light of the above, this paper proposes a number of solutions to tackle meta-overfitting on few-shot learning settings, such as few-shot sinusoid regression and few shot classification. Our proposed approaches demonstrate improved generalization performance compared to state-of-the-art baselines for learning in a non-mutually exclusive task setting. Overall, this paper aims to provide insights into tackling overfitting in meta-learning and to advance the field towards more robust and generalizable models.
The rapid growth of the Internet of Things fosters collaboration among connected devices for tasks like indoor localization. However, existing indoor localization solutions struggle with dynamic and harsh conditions, requiring extensive data collection and environment-specific calibration. These factors impede cooperation, scalability, and the utilization of prior research efforts. To address these challenges, we propose FeMLoc, a federated meta-learning framework for localization. FeMLoc operates in two stages: (i) collaborative meta-training where a global meta-model is created by training on diverse localization datasets from edge devices. (ii) Rapid adaptation for new environments, where the pre-trained global meta-model initializes the localization model, requiring only minimal fine-tuning with a small amount of new data. In this paper, we provide a detailed technical overview of FeMLoc, highlighting its unique approach to privacy-preserving meta-learning in the context of indoor localization. Our performance evaluation demonstrates the superiority of FeMLoc over state-of-the-art methods, enabling swift adaptation to new indoor environments with reduced calibration effort. Specifically, FeMLoc achieves up to 80.95% improvement in localization accuracy compared to the conventional baseline neural network (NN) approach after only 100 gradient steps. Alternatively, for a target accuracy of around 5m, FeMLoc achieves the same level of accuracy up to 82.21% faster than the baseline NN approach. This translates to FeMLoc requiring fewer training iterations, thereby significantly reducing fingerprint data collection and calibration efforts. Moreover, FeMLoc exhibits enhanced scalability, making it well-suited for location-aware massive connectivity driven by emerging wireless communication technologies.
Deep learning, a cutting-edge machine learning approach, outperforms traditional machine learning in identifying intricate structures in complex high-dimensional data, particularly in the domain of healthcare. This study focuses on classifying Magnetic Resonance Imaging (MRI) data for Alzheimer's disease (AD) by leveraging deep learning techniques characterized by state-of-the-art CNNs. Brain imaging techniques such as MRI have enabled the measurement of pathophysiological brain changes related to Alzheimer's disease. Alzheimer's disease is the leading cause of dementia in the elderly, and it is an irreversible brain illness that causes gradual cognitive function disorder. In this paper, we train some benchmark deep models individually for the approach of the solution and later use an ensembling approach to combine the effect of multiple CNNs towards the observation of higher recall and accuracy. Here, the model's effectiveness is evaluated using various methods, including stacking, majority voting, and the combination of models with high recall values. The majority voting performs better than the alternative modelling approach as the majority voting approach typically reduces the variance in the predictions. We report a test accuracy of 90% with a precision score of 0.90 and a recall score of 0.89 in our proposed approach. In future, this study can be extended to incorporate other types of medical data, including signals, images, and other data. The same or alternative datasets can be used with additional classifiers, neural networks, and AI techniques to enhance Alzheimer's detection.
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominantly rely on the intuition that alternating optimization between the context encoder and the policy can lead to performance improvements, as long as the context encoder follows the principle of maximizing the mutual information between the task variable $M$ and its latent representation $Z$ ($I(Z;M)$) while the policy adopts the standard offline reinforcement learning (RL) algorithms conditioning on the learned task representation.Despite promising results, the theoretical justification of performance improvements for such intuition remains underexplored.Inspired by the return discrepancy scheme in the model-based RL field, we find that the previous optimization framework can be linked with the general RL objective of maximizing the expected return, thereby explaining performance improvements. Furthermore, after scrutinizing this optimization framework, we observe that the condition for monotonic performance improvements does not consider the variation of the task representation. When these variations are considered, the previously established condition may no longer be sufficient to ensure monotonicity, thereby impairing the optimization process.We name this issue task representation shift and theoretically prove that the monotonic performance improvements can be guaranteed with appropriate context encoder updates.Our work opens up a new avenue for OMRL, leading to a better understanding between the task representation and performance improvements.
Utilizing deep learning (DL) techniques for radio-based positioning of user equipment (UE) through channel state information (CSI) fingerprints has demonstrated significant potential. DL models can extract complex characteristics from the CSI fingerprints of a particular environment and accurately predict the position of a UE. Nonetheless, the effectiveness of the DL model trained on CSI fingerprints is highly dependent on the particular training environment, limiting the trained model's applicability across different environments. This paper proposes a novel DL model structure consisting of two parts, where the first part aims at identifying features that are independent from any specific environment, while the second part combines those features in an environment specific way with the goal of positioning. To train such a two-part model, we propose the multi-environment meta-learning (MEML) approach for the first part to facilitate training across various environments, while the second part of the model is trained solely on data from a specific environment. Our findings indicate that employing the MEML approach for initializing the weights of the DL model for a new unseen environment significantly boosts the accuracy of UE positioning in the new target environment as well the reliability of its uncertainty estimation. This method outperforms traditional transfer learning methods, whether direct transfer learning (DTL) between environments or completely training from scratch with data from a new environment. The proposed approach is verified with real measurements for both line-of-sight (LOS) and non-LOS (NLOS) environments.
Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications. This paper builds upon the transformative concept of ``antifragility'' introduced by (Taleb, 2014) as a constructive design paradigm to not just withstand but benefit from volatility. We formally define antifragility in the context of online decision making as dynamic regret's strictly concave response to environmental variability, revealing limitations of current approaches focused on resisting rather than benefiting from nonstationarity. Our contribution lies in proposing potential computational pathways for engineering antifragility, grounding the concept in online learning theory and drawing connections to recent advancements in areas such as meta-learning, safe exploration, continual learning, multi-objective/quality-diversity optimization, and foundation models. By identifying promising mechanisms and future research directions, we aim to put antifragility on a rigorous theoretical foundation in machine learning. We further emphasize the need for clear guidelines, risk assessment frameworks, and interdisciplinary collaboration to ensure responsible application.
Developing accurate models for chemical reactors is often challenging due to the complexity of reaction kinetics and process dynamics. Traditional approaches require retraining models for each new system, limiting generalizability and efficiency. In this work, we take a step toward foundation models for chemical reactor modeling by introducing a neural network framework that generalizes across diverse reactor types and rapidly adapts to new chemical processes. Our approach leverages meta-learning to pretrain the model on a broad set of reactor dynamics, enabling efficient adaptation to unseen reactions with minimal data. To further enhance generalizability, we incorporate physics-informed fine-tuning, ensuring physically consistent adaptation to new reactor conditions. Our framework is evaluated across three integer-order fundamental reactor types - continuous stirred tank reactors, batch reactors, and plug flow reactors - demonstrating superior few-shot adaptation compared to conventional data-driven, physics-informed, and transfer learning approaches. By combining meta-learning with physics-informed adaptation, this work lays the foundation for a generalizable modeling framework, advancing the development of foundation models for chemical engineering applications. Source code is available at https://github.com/killingbear999/chemical-reactor-foundation-model.
Single object tracking is a vital task of many applications in critical fields. However, it is still considered one of the most challenging vision tasks. In recent years, computer vision, especially object tracking, witnessed the introduction or adoption of many novel techniques, setting new fronts for performance. In this survey, we visit some of the cutting-edge techniques in vision, such as Sequence Models, Generative Models, Self-supervised Learning, Unsupervised Learning, Reinforcement Learning, Meta-Learning, Continual Learning, and Domain Adaptation, focusing on their application in single object tracking. We propose a novel categorization of single object tracking methods based on novel techniques and trends. Also, we conduct a comparative analysis of the performance reported by the methods presented on popular tracking benchmarks. Moreover, we analyze the pros and cons of the presented approaches and present a guide for non-traditional techniques in single object tracking. Finally, we suggest potential avenues for future research in single-object tracking.
Meta-learning methods typically learn tasks under the assumption that all tasks are equally important. However, this assumption is often not valid. In real-world applications, tasks can vary both in their importance during different training stages and in whether they contain noisy labeled data or not, making a uniform approach suboptimal. To address these issues, we propose the Data-Efficient and Robust Task Selection (DERTS) algorithm, which can be incorporated into both gradient and metric-based meta-learning algorithms. DERTS selects weighted subsets of tasks from task pools by minimizing the approximation error of the full gradient of task pools in the meta-training stage. The selected tasks are efficient for rapid training and robust towards noisy label scenarios. Unlike existing algorithms, DERTS does not require any architecture modification for training and can handle noisy label data in both the support and query sets. Analysis of DERTS shows that the algorithm follows similar training dynamics as learning on the full task pools. Experiments show that DERTS outperforms existing sampling strategies for meta-learning on both gradient-based and metric-based meta-learning algorithms in limited data budget and noisy task settings.
In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this challenge, we propose a novel approach called Meta-learned Modality-weighted Knowledge Distillation (MetaKD), which enables multi-modal models to maintain high accuracy even when key modalities are missing. MetaKD adaptively estimates the importance weight of each modality through a meta-learning process. These learned importance weights guide a pairwise modality-weighted knowledge distillation process, allowing high-importance modalities to transfer knowledge to lower-importance ones, resulting in robust performance despite missing inputs. Unlike previous methods in the field, which are often task-specific and require significant modifications, our approach is designed to work in multiple tasks (e.g., segmentation and classification) with minimal adaptation. Experimental results on five prevalent datasets, including three Brain Tumor Segmentation datasets (BraTS2018, BraTS2019 and BraTS2020), the Alzheimer's Disease Neuroimaging Initiative (ADNI) classification dataset and the Audiovision-MNIST classification dataset, demonstrate the proposed model is able to outperform the compared models by a large margin.
Many industry verticals are confronted with small-sized tabular data. In this low-data regime, it is currently unclear whether the best performance can be expected from simple baselines, or more complex machine learning approaches that leverage meta-learning and ensembling. On 44 tabular classification datasets with sample sizes $\leq$ 500, we find that L2-regularized logistic regression performs similar to state-of-the-art automated machine learning (AutoML) frameworks (AutoPrognosis, AutoGluon) and off-the-shelf deep neural networks (TabPFN, HyperFast) on the majority of the benchmark datasets. We therefore recommend to consider logistic regression as the first choice for data-scarce applications with tabular data and provide practitioners with best practices for further method selection.