Meta-learning is characterized by its ability to learn how to learn, enabling the adaptation of learning strategies across different tasks. Recent research introduced the Meta-Thompson Sampling (Meta-TS), which meta-learns an unknown prior distribution sampled from a meta-prior by interacting with bandit instances drawn from it. However, its analysis was limited to Gaussian bandit. The contextual multi-armed bandit framework is an extension of the Gaussian Bandit, which challenges agent to utilize context vectors to predict the most valuable arms, optimally balancing exploration and exploitation to minimize regret over time. This paper introduces Meta-TSLB algorithm, a modified Meta-TS for linear contextual bandits. We theoretically analyze Meta-TSLB and derive an $ O((m+\log(m))\sqrt{n\log(n)})$ bound on its Bayes regret, in which $m$ represents the number of bandit instances, and $n$ the number of rounds of Thompson Sampling. Additionally, our work complements the analysis of Meta-TS for linear contextual bandits. The performance of Meta-TSLB is evaluated experimentally under different settings, and we experimente and analyze the generalization capability of Meta-TSLB, showcasing its potential to adapt to unseen instances.
Image Quality Assessment (IQA) remains an unresolved challenge in the field of computer vision, due to complex distortion conditions, diverse image content, and limited data availability. The existing Blind IQA (BIQA) methods heavily rely on extensive human annotations to train models, which is both labor-intensive and costly due to the demanding nature of creating IQA datasets. To mitigate the dependence on labeled samples, this paper introduces a novel Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA). This framework aims to fast adapt the powerful visual-language pre-trained model, CLIP, to downstream IQA tasks, significantly improving accuracy in scenarios with limited data. Specifically, the GRMP-IQA comprises two key modules: Meta-Prompt Pre-training Module and Quality-Aware Gradient Regularization. The Meta Prompt Pre-training Module leverages a meta-learning paradigm to pre-train soft prompts with shared meta-knowledge across different distortions, enabling rapid adaptation to various IQA tasks. On the other hand, the Quality-Aware Gradient Regularization is designed to adjust the update gradients during fine-tuning, focusing the model's attention on quality-relevant features and preventing overfitting to semantic information. Extensive experiments on five standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods under limited data setting, i.e., achieving SRCC values of 0.836 (vs. 0.760 on LIVEC) and 0.853 (vs. 0.812 on KonIQ). Notably, utilizing just 20\% of the training data, our GRMP-IQA outperforms most existing fully supervised BIQA methods.
Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model\&dataset\&test black-box meta attack tasks. Specifically, cross-model\&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model\&dataset and cross-model\&dataset\&test attacks, our MTGA outperforms the SOTA methods by 21.5\% and 11.3\% on mean mAP drop rate, respectively. The code of MTGA will be released after the paper is accepted.
Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit ICL are not always consistent. In this work, we propose a framework for evaluating in-context learning mechanisms, which we claim are a combination of retrieving internal knowledge and learning from in-context examples by focusing on regression tasks. First, we show that LLMs can perform regression on real-world datasets and then design experiments to measure the extent to which the LLM retrieves its internal knowledge versus learning from in-context examples. We argue that this process lies on a spectrum between these two extremes. We provide an in-depth analysis of the degrees to which these mechanisms are triggered depending on various factors, such as prior knowledge about the tasks and the type and richness of the information provided by the in-context examples. We employ three LLMs and utilize multiple datasets to corroborate the robustness of our findings. Our results shed light on how to engineer prompts to leverage meta-learning from in-context examples and foster knowledge retrieval depending on the problem being addressed.
Optimal selection of optimization algorithms is crucial for training deep learning models. The Adam optimizer has gained significant attention due to its efficiency and wide applicability. However, to enhance the adaptability of optimizers across diverse datasets, we propose an innovative optimization strategy by integrating the 'warped gradient descend'concept from Meta Learning into the Adam optimizer. In the conventional Adam optimizer, gradients are utilized to compute estimates of gradient mean and variance, subsequently updating model parameters. Our approach introduces a learnable distortion matrix, denoted as P, which is employed for linearly transforming gradients. This transformation slightly adjusts gradients during each iteration, enabling the optimizer to better adapt to distinct dataset characteristics. By learning an appropriate distortion matrix P, our method aims to adaptively adjust gradient information across different data distributions, thereby enhancing optimization performance. Our research showcases the potential of this novel approach through theoretical insights and empirical evaluations. Experimental results across various tasks and datasets validate the superiority of our optimizer that integrates the 'warped gradient descend' concept in terms of adaptability. Furthermore, we explore effective strategies for training the adaptation matrix P and identify scenarios where this method can yield optimal results. In summary, this study introduces an innovative approach that merges the 'warped gradient descend' concept from Meta Learning with the Adam optimizer. By introducing a learnable distortion matrix P within the optimizer, we aim to enhance the model's generalization capability across diverse data distributions, thus opening up new possibilities in the field of deep learning optimization.
Function and dysfunctions of neural systems are tied to the temporal evolution of neural states. The current limitations in showing their causal role stem largely from the absence of tools capable of probing the brain's internal state in real-time. This gap restricts the scope of experiments vital for advancing both fundamental and clinical neuroscience. Recent advances in real-time machine learning technologies, particularly in analyzing neural time series as nonlinear stochastic dynamical systems, are beginning to bridge this gap. These technologies enable immediate interpretation of and interaction with neural systems, offering new insights into neural computation. However, several significant challenges remain. Issues such as slow convergence rates, high-dimensional data complexities, structured noise, non-identifiability, and a general lack of inductive biases tailored for neural dynamics are key hurdles. Overcoming these challenges is crucial for the full realization of real-time neural data analysis for the causal investigation of neural computation and advanced perturbation based brain machine interfaces. In this paper, we provide a comprehensive perspective on the current state of the field, focusing on these persistent issues and outlining potential paths forward. We emphasize the importance of large-scale integrative neuroscience initiatives and the role of meta-learning in overcoming these challenges. These approaches represent promising research directions that could redefine the landscape of neuroscience experiments and brain-machine interfaces, facilitating breakthroughs in understanding brain function, and treatment of neurological disorders.
Learning new tasks by drawing on prior experience gathered from other (related) tasks is a core property of any intelligent system. Gradient-based meta-learning, especially MAML and its variants, has emerged as a viable solution to accomplish this goal. One problem MAML encounters is its computational and memory burdens needed to compute the meta-gradients. We propose a new first-order variant of MAML that we prove converges to a stationary point of the MAML objective, unlike other first-order variants. We also show that the MAML objective does not satisfy the smoothness assumption assumed in previous works; we show instead that its smoothness constant grows with the norm of the meta-gradient, which theoretically suggests the use of normalized or clipped-gradient methods compared to the plain gradient method used in previous works. We validate our theory on a synthetic experiment.
Data scarcity poses a serious threat to modern machine learning and artificial intelligence, as their practical success typically relies on the availability of big datasets. One effective strategy to mitigate the issue of insufficient data is to first harness information from other data sources possessing certain similarities in the study design stage, and then employ the multi-task or meta learning framework in the analysis stage. In this paper, we focus on multi-task (or multi-source) linear models whose coefficients across tasks share an invariant low-rank component, a popular structural assumption considered in the recent multi-task or meta learning literature. Under this assumption, we propose a new algorithm, called Meta Subspace Pursuit (abbreviated as Meta-SP), that provably learns this invariant subspace shared by different tasks. Under this stylized setup for multi-task or meta learning, we establish both the algorithmic and statistical guarantees of the proposed method. Extensive numerical experiments are conducted, comparing Meta-SP against several competing methods, including popular, off-the-shelf model-agnostic meta learning algorithms such as ANIL. These experiments demonstrate that Meta-SP achieves superior performance over the competing methods in various aspects.
Recently, the design of wireless receivers using deep neural networks (DNNs), known as deep receivers, has attracted extensive attention for ensuring reliable communication in complex channel environments. To adapt quickly to dynamic channels, online learning has been adopted to update the weights of deep receivers with over-the-air data (e.g., pilots). However, the fragility of neural models and the openness of wireless channels expose these systems to malicious attacks. To this end, understanding these attack methods is essential for robust receiver design. In this paper, we propose a transfer-based adversarial poisoning attack method for online receivers. Without knowledge of the attack target, adversarial perturbations are injected to the pilots, poisoning the online deep receiver and impairing its ability to adapt to dynamic channels and nonlinear effects. In particular, our attack method targets Deep Soft Interference Cancellation (DeepSIC)[1] using online meta-learning. As a classical model-driven deep receiver, DeepSIC incorporates wireless domain knowledge into its architecture. This integration allows it to adapt efficiently to time-varying channels with only a small number of pilots, achieving optimal performance in a multi-input and multi-output (MIMO) scenario. The deep receiver in this scenario has a number of applications in the field of wireless communication, which motivates our study of the attack methods targeting it. Specifically, we demonstrate the effectiveness of our attack in simulations on synthetic linear, synthetic nonlinear, static, and COST 2100 channels. Simulation results indicate that the proposed poisoning attack significantly reduces the performance of online receivers in rapidly changing scenarios.
Indoor robots rely on depth to perform tasks like navigation or obstacle detection, and single-image depth estimation is widely used to assist perception. Most indoor single-image depth prediction focuses less on model generalizability to unseen datasets, concerned with in-the-wild robustness for system deployment. This work leverages gradient-based meta-learning to gain higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied meta-learning of image classification associated with explicit class labels, no explicit task boundaries exist for continuous depth values tied to highly varying indoor environments regarding object arrangement and scene composition. We propose fine-grained task that treats each RGB-D mini-batch as a task in our meta-learning formulation. We first show that our method on limited data induces a much better prior (max 27.8% in RMSE). Then, finetuning on meta-learned initialization consistently outperforms baselines without the meta approach. Aiming at generalization, we propose zero-shot cross-dataset protocols and validate higher generalizability induced by our meta-initialization, as a simple and useful plugin to many existing depth estimation methods. The work at the intersection of depth and meta-learning potentially drives both research to step closer to practical robotic and machine perception usage.
In this paper, we consider a radio resource management (RRM) problem in the dynamic wireless networks, comprising multiple communication links that share the same spectrum resource. To achieve high network throughput while ensuring fairness across all links, we formulate a resilient power optimization problem with per-user minimum-rate constraints. We obtain the corresponding Lagrangian dual problem and parameterize all variables with neural networks, which can be trained in an unsupervised manner due to the provably acceptable duality gap. We develop a meta-learning approach with graph neural networks (GNNs) as parameterization that exhibits fast adaptation and scalability to varying network configurations. We formulate the objective of meta-learning by amalgamating the Lagrangian functions of different network configurations and utilize a first-order meta-learning algorithm, called Reptile, to obtain the meta-parameters. Numerical results verify that our method can efficiently improve the overall throughput and ensure the minimum rate performance. We further demonstrate that using the meta-parameters as initialization, our method can achieve fast adaptation to new wireless network configurations and reduce the number of required training data samples.
The growing privacy concerns surrounding face image data demand new techniques that can guarantee user privacy. One such face recognition technique that claims to achieve better user privacy is Federated Face Recognition (FRR), a subfield of Federated Learning (FL). However, FFR faces challenges due to the heterogeneity of the data, given the large number of classes that need to be handled. To overcome this problem, solutions are sought in the field of personalized FL. This work introduces three new data partitions based on the CelebA dataset, each with a different form of data heterogeneity. It also proposes Hessian-Free Model Agnostic Meta-Learning (HF-MAML) in an FFR setting. We show that HF-MAML scores higher in verification tests than current FFR models on three different CelebA data partitions. In particular, the verification scores improve the most in heterogeneous data partitions. To balance personalization with the development of an effective global model, an embedding regularization term is introduced for the loss function. This term can be combined with HF-MAML and is shown to increase global model verification performance. Lastly, this work performs a fairness analysis, showing that HF-MAML and its embedding regularization extension can improve fairness by reducing the standard deviation over the client evaluation scores.
Single-operator learning involves training a deep neural network to learn a specific operator, whereas recent work in multi-operator learning uses an operator embedding structure to train a single neural network on data from multiple operators. Thus, multi-operator learning is capable of predicting a range of operators within one model. In this work, we propose pretraining and fine-tuning strategies for solving PDEs using multi-operator learning. One key aspect is that by increasing the number of families of operators used in pretraining, a PDE foundation model can be fine-tuned to downstream tasks involving new PDEs with a limited number of samples, thus outperforming single operator neural networks. Specifically, a multi-operator learning model pre-trained with data from diverse PDE families can predict unseen operators after fine-tuning with only a limited number of operators from the new family, enabling them to serve as a data-free PDE solver. We also show that the proposed training and fine-tuning method is able to predict new operators in zero-shot prediction without samples. Additionally, we introduce a PDE-agnostic meta-learning algorithm to improve the adaptability of the model to various PDEs by providing a better parameter initialization process. To address the needs of applications with limited computing resources, we explore low-rank adaptation methods that reduce computational costs while enhancing solver accuracy. Lastly, by examining the scaling law with respect to the number of operator families, we establish and highlight its potential for broad adaptation in PDE-solving tasks.
Mathematical modeling in systems toxicology enables a comprehensive understanding of the effects of pharmaceutical substances on cardiac health. However, the complexity of these models limits their widespread application in early drug discovery. In this paper, we introduce a novel approach to solving parameterized models of cardiac action potentials by combining meta-learning techniques with Systems Biology-Informed Neural Networks (SBINNs). The proposed method, HyperSBINN, effectively addresses the challenge of predicting the effects of various compounds at different concentrations on cardiac action potentials, outperforming traditional differential equation solvers in speed. Our model efficiently handles scenarios with limited data and complex parameterized differential equations. The HyperSBINN model demonstrates robust performance in predicting APD90 values, indicating its potential as a reliable tool for modeling cardiac electrophysiology and aiding in preclinical drug development. This framework represents an advancement in computational modeling, offering a scalable and efficient solution for simulating and understanding complex biological systems.
Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data. Existing approaches, particularly Negative-Prototype-Based methods, generate negative prototypes based solely on known class data. However, as the unknown space is infinite while the known space is limited, these methods suffer from limited representation capability. To address this limitation, we propose a novel approach, termed \textbf{D}iversified \textbf{N}egative \textbf{P}rototypes \textbf{G}enerator (DNPG), which adopts the principle of "learning unknowns from unknowns." Our method leverages the unknown space information learned from base classes to generate more representative negative prototypes for novel classes. During the pre-training phase, we learn the unknown space representation of the base classes. This representation, along with inter-class relationships, is then utilized in the meta-learning process to construct negative prototypes for novel classes. To prevent prototype collapse and ensure adaptability to varying data compositions, we introduce the Swap Alignment (SA) module. Our DNPG model, by learning from the unknown space, generates negative prototypes that cover a broader unknown space, thereby achieving state-of-the-art performance on three standard FSOR datasets.
Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner's guide to continual multimodal pretraining for real-world deployment. Our benchmark and code is here: https://github.com/ExplainableML/fomo_in_flux.
This paper presents a study on few-shot classification in the context of histopathology images. While few-shot learning has been studied for natural image classification, its application to histopathology is relatively unexplored. Given the scarcity of labeled data in medical imaging and the inherent challenges posed by diverse tissue types and data preparation techniques, this research evaluates the performance of state-of-the-art few-shot learning methods for various scenarios on histology data. We have considered four histopathology datasets for few-shot histopathology image classification and have evaluated 5-way 1-shot, 5-way 5-shot and 5-way 10-shot scenarios with a set of state-of-the-art classification techniques. The best methods have surpassed an accuracy of 70%, 80% and 85% in the cases of 5-way 1-shot, 5-way 5-shot and 5-way 10-shot cases, respectively. We found that for histology images popular meta-learning approaches is at par with standard fine-tuning and regularization methods. Our experiments underscore the challenges of working with images from different domains and underscore the significance of unbiased and focused evaluations in advancing computer vision techniques for specialized domains, such as histology images.
Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks, namely, synthetic speech (SS), voice conversion (VC), replay, twins and impersonation, especially in the case of unseen synthetic spoofing attacks. A reliable and robust spoofing detection system can act as a security gate to filter out spoofing attacks instead of having them reach the ASV system. A weighted additive angular margin loss is proposed to address the data imbalance issue, and different margins has been assigned to improve generalization to unseen spoofing attacks in this study. Meanwhile, we incorporate a meta-learning loss function to optimize differences between the embeddings of support versus query set in order to learn a spoofing-category-independent embedding space for utterances. Furthermore, we craft adversarial examples by adding imperceptible perturbations to spoofing speech as a data augmentation strategy, then we use an auxiliary batch normalization (BN) to guarantee that corresponding normalization statistics are performed exclusively on the adversarial examples. Additionally, A simple attention module is integrated into the residual block to refine the feature extraction process. Evaluation results on the Logical Access (LA) track of the ASVspoof 2019 corpus provides confirmation of our proposed approaches' effectiveness in terms of a pooled EER of 0.87%, and a min t-DCF of 0.0277. These advancements offer effective options to reduce the impact of spoofing attacks on voice recognition/authentication systems.
Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks, which is regarded as a key factor in their success. However, the in-depth theoretical understanding of the learning dynamics and the origin of the shared representation remains underdeveloped. In this work, we investigate the meta-learning dynamics of nonlinear two-layer neural networks trained on streaming tasks in the teacher-student scenario. Through the lens of statistical physics analysis, we characterize the macroscopic behavior of the meta-training processes, the formation of the shared representation, and the generalization ability of the model on new tasks. The analysis also points to the importance of the choice of certain hyperparameters of the learning algorithms.
Stochastic compositional minimax problems are prevalent in machine learning, yet there are only limited established on the convergence of this class of problems. In this paper, we propose a formal definition of the stochastic compositional minimax problem, which involves optimizing a minimax loss with a compositional structure either in primal , dual, or both primal and dual variables. We introduce a simple yet effective algorithm, stochastically Corrected stOchastic gradient Descent Ascent (CODA), which is a descent ascent type algorithm with compositional correction steps, and establish its convergence rate in aforementioned three settings. In the presence of the compositional structure in primal, the objective function typically becomes nonconvex in primal due to function composition. Thus, we consider the nonconvex-strongly-concave and nonconvex-concave settings and show that CODA can efficiently converge to a stationary point. In the case of composition on the dual, the objective function becomes nonconcave in the dual variable, and we demonstrate convergence in the strongly-convex-nonconcave and convex-nonconcave setting. In the case of composition on both variables, the primal and dual variables may lose convexity and concavity, respectively. Therefore, we anaylze the convergence in weakly-convex-weakly-concave setting. We also give a variance reduction version algorithm, CODA+, which achieves the best known rate on nonconvex-strongly-concave and nonconvex-concave compositional minimax problem. This work initiates the theoretical study of the stochastic compositional minimax problem on various settings and may inform modern machine learning scenarios such as domain adaptation or robust model-agnostic meta-learning.