Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even the most basic tasks. Meta-learning aims to resolve this issue by leveraging past experiences from similar learning tasks to embed the appropriate inductive biases into the learning system. Historically methods for meta-learning components such as optimizers, parameter initializations, and more have led to significant performance increases. This thesis aims to explore the concept of meta-learning to improve performance, through the often-overlooked component of the loss function. The loss function is a vital component of a learning system, as it represents the primary learning objective, where success is determined and quantified by the system's ability to optimize for that objective successfully.
Fairness-aware domain generalization (FairDG) has emerged as a critical challenge for deploying trustworthy AI systems, particularly in scenarios involving distribution shifts. Traditional methods for addressing fairness have failed in domain generalization due to their lack of consideration for distribution shifts. Although disentanglement has been used to tackle FairDG, it is limited by its strong assumptions. To overcome these limitations, we propose Fairness-aware Classifier-Guided Score-based Diffusion Models (FADE) as a novel approach to effectively address the FairDG issue. Specifically, we first pre-train a score-based diffusion model (SDM) and two classifiers to equip the model with strong generalization capabilities across different domains. Then, we guide the SDM using these pre-trained classifiers to effectively eliminate sensitive information from the generated data. Finally, the generated fair data is used to train downstream classifiers, ensuring robust performance under new data distributions. Extensive experiments on three real-world datasets demonstrate that FADE not only enhances fairness but also improves accuracy in the presence of distribution shifts. Additionally, FADE outperforms existing methods in achieving the best accuracy-fairness trade-offs.
We consider the problem of user-adaptive 3D gaze estimation. The performance of person-independent gaze estimation is limited due to interpersonal anatomical differences. Our goal is to provide a personalized gaze estimation model specifically adapted to a target user. Previous work on user-adaptive gaze estimation requires some labeled images of the target person data to fine-tune the model at test time. However, this can be unrealistic in real-world applications, since it is cumbersome for an end-user to provide labeled images. In addition, previous work requires the training data to have both gaze labels and person IDs. This data requirement makes it infeasible to use some of the available data. To tackle these challenges, this paper proposes a new problem called efficient label-free user adaptation in gaze estimation. Our model only needs a few unlabeled images of a target user for the model adaptation. During offline training, we have some labeled source data without person IDs and some unlabeled person-specific data. Our proposed method uses a meta-learning approach to learn how to adapt to a new user with only a few unlabeled images. Our key technical innovation is to use a generalization bound from domain adaptation to define the loss function in meta-learning, so that our method can effectively make use of both the labeled source data and the unlabeled person-specific data during training. Extensive experiments validate the effectiveness of our method on several challenging benchmarks.
Representations for black-box optimisation methods (such as evolutionary algorithms) are traditionally constructed using a delicate manual process. This is in contrast to the representation that maps DNAs to phenotypes in biological organisms, which is at the hear of biological complexity and evolvability. Additionally, the core of this process is fundamentally the same across nearly all forms of life, reflecting their shared evolutionary origin. Generative models have shown promise in being learnable representations for black-box optimisation but they are not per se designed to be easily searchable. Here we present a system that can meta-learn such representation by directly optimising for a representation's ability to generate quality-diversity. In more detail, we show our meta-learning approach can find one Neural Cellular Automata, in which cells can attend to different parts of a "DNA" string genome during development, enabling it to grow different solvable 2D maze structures. We show that the evolved genotype-to-phenotype mappings become more and more evolvable, not only resulting in a faster search but also increasing the quality and diversity of grown artefacts.
Many high-stakes applications require machine learning models that protect user privacy and provide well-calibrated, accurate predictions. While Differential Privacy (DP) is the gold standard for protecting user privacy, standard DP mechanisms typically significantly impair performance. One approach to mitigating this issue is pre-training models on simulated data before DP learning on the private data. In this work we go a step further, using simulated data to train a meta-learning model that combines the Convolutional Conditional Neural Process (ConvCNP) with an improved functional DP mechanism of Hall et al. [2013] yielding the DPConvCNP. DPConvCNP learns from simulated data how to map private data to a DP predictive model in one forward pass, and then provides accurate, well-calibrated predictions. We compare DPConvCNP with a DP Gaussian Process (GP) baseline with carefully tuned hyperparameters. The DPConvCNP outperforms the GP baseline, especially on non-Gaussian data, yet is much faster at test time and requires less tuning.
Learning-based approaches have witnessed great successes in blind single image super-resolution (SISR) tasks, however, handcrafted kernel priors and learning based kernel priors are typically required. In this paper, we propose a Meta-learning and Markov Chain Monte Carlo (MCMC) based SISR approach to learn kernel priors from organized randomness. In concrete, a lightweight network is adopted as kernel generator, and is optimized via learning from the MCMC simulation on random Gaussian distributions. This procedure provides an approximation for the rational blur kernel, and introduces a network-level Langevin dynamics into SISR optimization processes, which contributes to preventing bad local optimal solutions for kernel estimation. Meanwhile, a meta-learning-based alternating optimization procedure is proposed to optimize the kernel generator and image restorer, respectively. In contrast to the conventional alternating minimization strategy, a meta-learning-based framework is applied to learn an adaptive optimization strategy, which is less-greedy and results in better convergence performance. These two procedures are iteratively processed in a plug-and-play fashion, for the first time, realizing a learning-based but plug-and-play blind SISR solution in unsupervised inference. Extensive simulations demonstrate the superior performance and generalization ability of the proposed approach when comparing with state-of-the-arts on synthesis and real-world datasets. The code is available at https://github.com/XYLGroup/MLMC.
Band selection plays a crucial role in hyperspectral image classification by removing redundant and noisy bands and retaining discriminative ones. However, most existing deep learning-based methods are aimed at dealing with a specific band selection dataset, and need to retrain parameters for new datasets, which significantly limits their generalizability.To address this issue, a novel multi-teacher multi-objective meta-learning network (M$^3$BS) is proposed for zero-shot hyperspectral band selection. In M$^3$BS, a generalizable graph convolution network (GCN) is constructed to generate dataset-agnostic base, and extract compatible meta-knowledge from multiple band selection tasks. To enhance the ability of meta-knowledge extraction, multiple band selection teachers are introduced to provide diverse high-quality experiences.strategy Finally, subsequent classification tasks are attached and jointly optimized with multi-teacher band selection tasks through multi-objective meta-learning in an end-to-end trainable way. Multi-objective meta-learning guarantees to coordinate diverse optimization objectives automatically and adapt to various datasets simultaneously. Once the optimization is accomplished, the acquired meta-knowledge can be directly transferred to unseen datasets without any retraining or fine-tuning. Experimental results demonstrate the effectiveness and efficiency of our proposed method on par with state-of-the-art baselines for zero-shot hyperspectral band selection.
The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address this challenging task by learning how to learn new tasks by embedding inductive biases informed by prior learning experiences into the components of the learning algorithm. In this work, we build upon prior research and propose Neural Procedural Bias Meta-Learning (NPBML), a novel framework designed to meta-learn task-adaptive procedural biases. Our approach aims to consolidate recent advancements in meta-learned initializations, optimizers, and loss functions by learning them simultaneously and making them adapt to each individual task to maximize the strength of the learned inductive biases. This imbues each learning task with a unique set of procedural biases which is specifically designed and selected to attain strong learning performance in only a few gradient steps. The experimental results show that by meta-learning the procedural biases of a neural network, we can induce strong inductive biases towards a distribution of learning tasks, enabling robust learning performance across many well-established few-shot learning benchmarks.
Sharpness-aware minimization (SAM) has been instrumental in improving deep neural network training by minimizing both the training loss and the sharpness of the loss landscape, leading the model into flatter minima that are associated with better generalization properties. In another aspect, Model-Agnostic Meta-Learning (MAML) is a framework designed to improve the adaptability of models. MAML optimizes a set of meta-models that are specifically tailored for quick adaptation to multiple tasks with minimal fine-tuning steps and can generalize well with limited data. In this work, we explore the connection between SAM and MAML in enhancing model generalization. We introduce Agnostic-SAM, a novel approach that combines the principles of both SAM and MAML. Agnostic-SAM adapts the core idea of SAM by optimizing the model toward wider local minima using training data, while concurrently maintaining low loss values on validation data. By doing so, it seeks flatter minima that are not only robust to small perturbations but also less vulnerable to data distributional shift problems. Our experimental results demonstrate that Agnostic-SAM significantly improves generalization over baselines across a range of datasets and under challenging conditions such as noisy labels or data limitation.
To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set. Such an adjustment procedure can be cast within a meta-learning framework. However, naive integration of fairness goals via meta-learning can cause hypergradient conflicts for subgroups, resulting in unstable convergence and compromising model performance and fairness. To navigate this issue, we frame the resolution of hypergradient conflicts as a multi-player cooperative bargaining game. We introduce a two-stage meta-learning framework in which the first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model toward the Pareto front, and the second stage optimizes with respect to specific fairness goals. Our method is supported by theoretical results, notably a proof of the NBS for gradient aggregation free from linear independence assumptions, a proof of Pareto improvement, and a proof of monotonic improvement in validation loss. We also show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.
In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and models publicly, we aim to empower communities with limited linguistic resources and foster further innovation in the field of speech technology.
Despite the rapid expansion of smart grids and large volumes of data at the individual consumer level, there are still various cases where adequate data collection to train accurate load forecasting models is challenging or even impossible. This paper proposes adapting an established model-agnostic meta-learning algorithm for short-term load forecasting in the context of few-shot learning. Specifically, the proposed method can rapidly adapt and generalize within any unknown load time series of arbitrary length using only minimal training samples. In this context, the meta-learning model learns an optimal set of initial parameters for a base-level learner recurrent neural network. The proposed model is evaluated using a dataset of historical load consumption data from real-world consumers. Despite the examined load series' short length, it produces accurate forecasts outperforming transfer learning and task-specific machine learning methods by $12.5\%$. To enhance robustness and fairness during model evaluation, a novel metric, mean average log percentage error, is proposed that alleviates the bias introduced by the commonly used MAPE metric. Finally, a series of studies to evaluate the model's robustness under different hyperparameters and time series lengths is also conducted, demonstrating that the proposed approach consistently outperforms all other models.
Multitude of deep learning models have been proposed for node classification in graphs. However, they tend to perform poorly under labeled-data scarcity. Although Few-shot learning for graphs has been introduced to overcome this problem, the existing models are not easily adaptable for generic graph learning frameworks like Graph Neural Networks (GNNs). Our work proposes an Uncertainty Estimator framework that can be applied on top of any generic GNN backbone network (which are typically designed for supervised/semi-supervised node classification) to improve the node classification performance. A neural network is used to model the Uncertainty Estimator as a probability distribution rather than probabilistic discrete scalar values. We train these models under the classic episodic learning paradigm in the $n$-way, $k$-shot fashion, in an end-to-end setting. Our work demonstrates that implementation of the uncertainty estimator on a GNN backbone network improves the classification accuracy under Few-shot setting without any meta-learning specific architecture. We conduct experiments on multiple datasets under different Few-shot settings and different GNN-based backbone networks. Our method outperforms the baselines, which demonstrates the efficacy of the Uncertainty Estimator for Few-shot node classification on graphs with a GNN.
Model agnostic meta-learning (MAML) is one of the most widely used gradient-based meta-learning, consisting of two optimization loops: an inner loop and outer loop. MAML learns the new task from meta-initialization parameters with an inner update and finds the meta-initialization parameters in the outer loop. In general, the injection of noise into the gradient of the model for augmenting the gradient is one of the widely used regularization methods. In this work, we propose a novel cooperative meta-learning framework dubbed CML which leverages gradient-level regularization with gradient augmentation. We inject learnable noise into the gradient of the model for the model generalization. The key idea of CML is introducing the co-learner which has no inner update but the outer loop update to augment gradients for finding better meta-initialization parameters. Since the co-learner does not update in the inner loop, it can be easily deleted after meta-training. Therefore, CML infers with only meta-learner without additional cost and performance degradation. We demonstrate that CML is easily applicable to gradient-based meta-learning methods and CML leads to increased performance in few-shot regression, few-shot image classification and few-shot node classification tasks. Our codes are at https://github.com/JJongyn/CML.
Large language models (LLMs) exhibit an intriguing ability to learn a novel task from in-context examples presented in a demonstration, termed in-context learning (ICL). Understandably, a swath of research has been dedicated to uncovering the theories underpinning ICL. One popular hypothesis explains ICL by task selection. LLMs identify the task based on the demonstration and generalize it to the prompt. Another popular hypothesis is that ICL is a form of meta-learning, i.e., the models learn a learning algorithm at pre-training time and apply it to the demonstration. Finally, a third hypothesis argues that LLMs use the demonstration to select a composition of tasks learned during pre-training to perform ICL. In this paper, we empirically explore these three hypotheses that explain LLMs' ability to learn in context with a suite of experiments derived from common text classification tasks. We invalidate the first two hypotheses with counterexamples and provide evidence in support of the last hypothesis. Our results suggest an LLM could learn a novel task in context via composing tasks learned during pre-training.
We propose a meta-learning method for positive and unlabeled (PU) classification, which improves the performance of binary classifiers obtained from only PU data in unseen target tasks. PU learning is an important problem since PU data naturally arise in real-world applications such as outlier detection and information retrieval. Existing PU learning methods require many PU data, but sufficient data are often unavailable in practice. The proposed method minimizes the test classification risk after the model is adapted to PU data by using related tasks that consist of positive, negative, and unlabeled data. We formulate the adaptation as an estimation problem of the Bayes optimal classifier, which is an optimal classifier to minimize the classification risk. The proposed method embeds each instance into a task-specific space using neural networks. With the embedded PU data, the Bayes optimal classifier is estimated through density-ratio estimation of PU densities, whose solution is obtained as a closed-form solution. The closed-form solution enables us to efficiently and effectively minimize the test classification risk. We empirically show that the proposed method outperforms existing methods with one synthetic and three real-world datasets.
Meta-learning involves multiple learners, each dedicated to specific tasks, collaborating in a data-constrained setting. In current meta-learning methods, task learners locally learn models from sensitive data, termed support sets. These task learners subsequently share model-related information, such as gradients or loss values, which is computed using another part of the data termed query set, with a meta-learner. The meta-learner employs this information to update its meta-knowledge. Despite the absence of explicit data sharing, privacy concerns persist. This paper examines potential data leakage in a prominent metalearning algorithm, specifically Model-Agnostic Meta-Learning (MAML). In MAML, gradients are shared between the metalearner and task-learners. The primary objective is to scrutinize the gradient and the information it encompasses about the task dataset. Subsequently, we endeavor to propose membership inference attacks targeting the task dataset containing support and query sets. Finally, we explore various noise injection methods designed to safeguard the privacy of task data and thwart potential attacks. Experimental results demonstrate the effectiveness of these attacks on MAML and the efficacy of proper noise injection methods in countering them.
Decoupling the illumination in 3D scenes is crucial for novel view synthesis and relighting. In this paper, we propose a novel method for representing a scene illuminated by a point light using a set of relightable 3D Gaussian points. Inspired by the Blinn-Phong model, our approach decomposes the scene into ambient, diffuse, and specular components, enabling the synthesis of realistic lighting effects. To facilitate the decomposition of geometric information independent of lighting conditions, we introduce a novel bilevel optimization-based meta-learning framework. The fundamental idea is to view the rendering tasks under various lighting positions as a multi-task learning problem, which our meta-learning approach effectively addresses by generalizing the learned Gaussian geometries not only across different viewpoints but also across diverse light positions. Experimental results demonstrate the effectiveness of our approach in terms of training efficiency and rendering quality compared to existing methods for free-viewpoint relighting.
In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more classical literature of statistical machine learning, many models have sequential Bayesian update rules that yield the same learning outcome as the batch training, i.e., they are completely immune to catastrophic forgetting. However, they are often overly simple to model complex real-world data. In this work, we adopt the meta-learning paradigm to combine the strong representational power of neural networks and simple statistical models' robustness to forgetting. In our novel meta-continual learning framework, continual learning takes place only in statistical models via ideal sequential Bayesian update rules, while neural networks are meta-learned to bridge the raw data and the statistical models. Since the neural networks remain fixed during continual learning, they are protected from catastrophic forgetting. This approach not only achieves significantly improved performance but also exhibits excellent scalability. Since our approach is domain-agnostic and model-agnostic, it can be applied to a wide range of problems and easily integrated with existing model architectures.
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language is a rich modality that can be used to guide visual learning. In this work, we experiment with a multi-modal architecture for few-shot learning that consists of three components: a classifier, an auxiliary network, and a bridge network. While the classifier performs the main classification task, the auxiliary network learns to predict language representations from the same input, and the bridge network transforms high-level features of the auxiliary network into modulation parameters for layers of the few-shot classifier using conditional batch normalization. The bridge should encourage a form of lightweight semantic alignment between language and vision which could be useful for the classifier. However, after evaluating the proposed approach on two popular few-shot classification benchmarks we find that a) the improvements do not reproduce across benchmarks, and b) when they do, the improvements are due to the additional compute and parameters introduced by the bridge network. We contribute insights and recommendations for future work in multi-modal meta-learning, especially when using language representations.