Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditional manual tuning. Despite their efficiency in model deployments, most NAS algorithms target a single task on a fixed hardware system. However, real-life few-shot learning environments often cover a great number of tasks (T ) and deployments on a wide variety of hardware platforms (H ). The combinatorial search complexity T times H creates a fundamental search efficiency challenge if one naively applies existing NAS methods to these scenarios. To overcome this issue, we show, for the first time, how to rapidly adapt model architectures to new tasks in a many-task many-hardware few-shot learning setup by integrating Model Agnostic Meta Learning (MAML) into the NAS flow. The proposed NAS method (H-Meta-NAS) is hardware-aware and performs optimisation in the MAML framework. H-Meta-NAS shows a Pareto dominance compared to a variety of NAS and manual baselines in popular few-shot learning benchmarks with various hardware platforms and constraints. In particular, on the 5-way 1-shot Mini-ImageNet classification task, the proposed method outperforms the best manual baseline by a large margin (5.21% in accuracy) using 60% less computation.
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task. However, merely learning the knowledge from the historical tasks, adopted by current meta-learning algorithms, may not generalize well to testing tasks when they are not well-supported by training tasks. This paper studies a low-resource text classification problem and bridges the gap between meta-training and meta-testing tasks by leveraging the external knowledge bases. Specifically, we propose KGML to introduce additional representation for each sentence learned from the extracted sentence-specific knowledge graph. The extensive experiments on three datasets demonstrate the effectiveness of KGML under both supervised adaptation and unsupervised adaptation settings.
Meta-learning empowers artificial intelligence to increase its efficiency by learning how to learn. Unlocking this potential involves overcoming a challenging meta-optimisation problem. We propose an algorithm that tackles this problem by letting the meta-learner teach itself. The algorithm first bootstraps a target from the meta-learner, then optimises the meta-learner by minimising the distance to that target under a chosen (pseudo-)metric. Focusing on meta-learning with gradients, we establish conditions that guarantee performance improvements and show that the metric can control meta-optimisation. Meanwhile, the bootstrapping mechanism can extend the effective meta-learning horizon without requiring backpropagation through all updates. We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark and demonstrate that it yields both performance and efficiency gains in multi-task meta-learning. Finally, we explore how bootstrapping opens up new possibilities and find that it can meta-learn efficient exploration in an epsilon-greedy Q-learning agent, without backpropagating through the update rule.
We apply a reinforcement meta-learning framework to optimize an integrated and adaptive guidance and flight control system for an air-to-air missile. The system is implemented as a policy that maps navigation system outputs directly to commanded rates of change for the missile's control surface deflections. The system induces intercept trajectories against a maneuvering target that satisfy control constraints on fin deflection angles, and path constraints on look angle and load. We test the optimized system in a six degrees-of-freedom simulator that includes a non-linear radome model and a strapdown seeker model, and demonstrate that the system adapts to both a large flight envelope and off-nominal flight conditions including perturbation of aerodynamic coefficient parameters and center of pressure locations, and flexible body dynamics. Moreover, we find that the system is robust to the parasitic attitude loop induced by radome refraction and imperfect seeker stabilization. We compare our system's performance to a longitudinal model of proportional navigation coupled with a three loop autopilot, and find that our system outperforms this benchmark by a large margin. Additional experiments investigate the impact of removing the recurrent layer from the policy and value function networks, performance with an infrared seeker, and flexible body dynamics.
Artificial neural networks (ANNs) are typically confined to accomplishing pre-defined tasks by learning a set of static parameters. In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e.g., meta-learning. Among various biologically inspired learning rules, Hebbian plasticity updates the neural network weights using local signals without the guide of an explicit target function, thus enabling an agent to learn automatically without human efforts. However, typical plastic ANNs using a large amount of meta-parameters violate the nature of the genomics bottleneck and potentially deteriorate the generalization capacity. This work proposes a new learning paradigm decomposing those connection-dependent plasticity rules into neuron-dependent rules thus accommodating $\Theta(n^2)$ learnable parameters with only $\Theta(n)$ meta-parameters. We also thoroughly study the effect of different neural modulation on plasticity. Our algorithms are tested in challenging random 2D maze environments, where the agents have to use their past experiences to shape the neural connections and improve their performances for the future. The results of our experiment validate the following: 1. Plasticity can be adopted to continually update a randomly initialized RNN to surpass pre-trained, more sophisticated recurrent models, especially when coming to long-term memorization. 2. Following the genomics bottleneck, the proposed decomposed plasticity can be comparable to or even more effective than canonical plasticity rules in some instances.
Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels. Recent methods develop learning-based algorithms to learn sample re-weighting strategies jointly with model training based on the frameworks of reinforcement learning and meta learning. However, depending on additional unbiased reward data is limiting their general applicability. Furthermore, existing learning-based sample re-weighting methods require nested optimizations of models and weighting parameters, which requires expensive second-order computation. This paper addresses these two problems and presents a novel learning-based fast sample re-weighting (FSR) method that does not require additional reward data. The method is based on two key ideas: learning from history to build proxy reward data and feature sharing to reduce the optimization cost. Our experiments show the proposed method achieves competitive results compared to state of the arts on label noise robustness and long-tailed recognition, and does so while achieving significantly improved training efficiency. The source code is publicly available at https://github.com/google-research/google-research/tree/master/ieg.
We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches resort to the meta-learning paradigm, where the model accumulates inductive bias through learning many training tasks so as to solve a new unseen few-shot task. In contrast, we propose a simple approach to exploit unlabeled data accompanying the few-shot task for improving few-shot performance. Firstly, we propose a Dependency Maximization method based on the Hilbert-Schmidt norm of the cross-covariance operator, which maximizes the statistical dependency between the embedded feature of those unlabeled data and their label predictions, together with the supervised loss over the support set. We then use the obtained model to infer the pseudo-labels for those unlabeled data. Furthermore, we propose anInstance Discriminant Analysis to evaluate the credibility of each pseudo-labeled example and select the most faithful ones into an augmented support set to retrain the model as in the first step. We iterate the above process until the pseudo-labels for the unlabeled data becomes stable. Following the standard transductive and semi-supervised FSL setting, our experiments show that the proposed method out-performs previous state-of-the-art methods on four widely used benchmarks, including mini-ImageNet, tiered-ImageNet, CUB, and CIFARFS.
Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis. Despite recent advances with deep-based approaches, labeling samples (pixels) for training models is laborious and, in some cases, unfeasible. In this paper, we present two novel meta learning methods, named WeaSeL and ProtoSeg, for the few-shot semantic segmentation task with sparse annotations. We conducted extensive evaluation of the proposed methods in different applications (12 datasets) in medical imaging and agricultural remote sensing, which are very distinct fields of knowledge and usually subject to data scarcity. The results demonstrated the potential of our method, achieving suitable results for segmenting both coffee/orange crops and anatomical parts of the human body in comparison with full dense annotation.
While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles, and goals) that were not considered during the design or the training of these agents. In this spirit, in this paper, we consider the problem of training a provably safe Neural Network (NN) controller for uncertain nonlinear dynamical systems that can generalize to new tasks that were not present in the training data while preserving strong safety guarantees. Our approach is to learn a set of NN controllers during the training phase. When the task becomes available at runtime, our framework will carefully select a subset of these NN controllers and compose them to form the final NN controller. Critical to our approach is the ability to compute a finite-state abstraction of the nonlinear dynamical system. This abstract model captures the behavior of the closed-loop system under all possible NN weights, and is used to train the NNs and compose them when the task becomes available. We provide theoretical guarantees that govern the correctness of the resulting NN. We evaluated our approach on the problem of controlling a wheeled robot in cluttered environments that were not present in the training data.
In this paper, we consider the problem of power control for a wireless network with an arbitrarily time-varying topology, including the possible addition or removal of nodes. A data-driven design methodology that leverages graph neural networks (GNNs) is adopted in order to efficiently parametrize the power control policy mapping the channel state information (CSI) to transmit powers. The specific GNN architecture, known as random edge GNN (REGNN), defines a non-linear graph convolutional filter whose spatial weights are tied to the channel coefficients. While prior work assumed a joint training approach whereby the REGNN-based policy is shared across all topologies, this paper targets adaptation of the power control policy based on limited CSI data regarding the current topology. To this end, we propose a novel modular meta-learning technique that enables the efficient optimization of module assignment. While black-box meta-learning optimizes a general-purpose adaptation procedure via (stochastic) gradient descent, modular meta-learning finds a set of reusable modules that can form components of a solution for any new network topology. Numerical results validate the benefits of meta-learning for power control problems over joint training schemes, and demonstrate the advantages of modular meta-learning when data availability is extremely limited.
Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data distributions. Existing CL models often save a large number of old examples and stochastically revisit previously seen data to retain old knowledge. However, the occupied memory size keeps enlarging along with accumulating seen data. Hereby, we propose a memory-efficient CL method by storing a few samples to achieve good performance. We devise a dynamic prototype-guided memory replay module and incorporate it into an online meta-learning model. We conduct extensive experiments on text classification and investigate the effect of training set orders on CL model performance. The experimental results testify the superiority of our method in terms of forgetting mitigation and efficiency.
Existing machines are functionally specific tools that were made for easy prediction and control. Tomorrow's machines may be closer to biological systems in their mutability, resilience, and autonomy. But first they must be capable of learning and retaining new information without being exposed to it arbitrarily often. Past efforts to engineer such systems have sought to build or regulate artificial neural networks using disjoint sets of weights that are uniquely sensitive to specific tasks or inputs. This has not yet enabled continual learning over long sequences of previously unseen data without corrupting existing knowledge: a problem known as catastrophic forgetting. In this paper, we introduce a system that can learn sequentially over previously unseen datasets (ImageNet, CIFAR-100) with little forgetting over time. This is done by controlling the activity of weights in a convolutional neural network on the basis of inputs using top-down regulation generated by a second feed-forward neural network. We find that our method learns continually under domain transfer with sparse bursts of activity in weights that are recycled across tasks, rather than by maintaining task-specific modules. Sparse synaptic bursting is found to balance activity and suppression such that new functions can be learned without corrupting extant knowledge, thus mirroring the balance of order and disorder in systems at the edge of chaos. This behavior emerges during a prior pre-training (or 'meta-learning') phase in which regulated synapses are selectively disinhibited, or grown, from an initial state of uniform suppression through prediction error minimization.
Despite impressive results of language models for named entity recognition (NER), their generalization to varied textual genres, a growing entity type set, and new entities remains a challenge. Collecting thousands of annotations in each new case for training or fine-tuning is expensive and time-consuming. In contrast, humans can easily identify named entities given some simple instructions. Inspired by this, we challenge the reliance on large datasets and study pre-trained language models for NER in a meta-learning setup. First, we test named entity typing (NET) in a zero-shot transfer scenario. Then, we perform NER by giving few examples at inference. We propose a method to select seen and rare / unseen names when having access only to the pre-trained model and report results on these groups. The results show: auto-regressive language models as meta-learners can perform NET and NER fairly well especially for regular or seen names; name irregularity when often present for a certain entity type can become an effective exploitable cue; names with words foreign to the model have the most negative impact on results; the model seems to rely more on name than context cues in few-shot NER.
In this paper, given a small bag of images, each containing a common but latent predicate, we are interested in localizing visual subject-object pairs connected via the common predicate in each of the images. We refer to this novel problem as visual relationship co-localization or VRC as an abbreviation. VRC is a challenging task, even more so than the well-studied object co-localization task. This becomes further challenging when using just a few images, the model has to learn to co-localize visual subject-object pairs connected via unseen predicates. To solve VRC, we propose an optimization framework to select a common visual relationship in each image of the bag. The goal of the optimization framework is to find the optimal solution by learning visual relationship similarity across images in a few-shot setting. To obtain robust visual relationship representation, we utilize a simple yet effective technique that learns relationship embedding as a translation vector from visual subject to visual object in a shared space. Further, to learn visual relationship similarity, we utilize a proven meta-learning technique commonly used for few-shot classification tasks. Finally, to tackle the combinatorial complexity challenge arising from an exponential number of feasible solutions, we use a greedy approximation inference algorithm that selects approximately the best solution. We extensively evaluate our proposed framework on variations of bag sizes obtained from two challenging public datasets, namely VrR-VG and VG-150, and achieve impressive visual co-localization performance.
Meta-learning is widely used for few-shot slot tagging in task of few-shot learning. The performance of existing methods is, however, seriously affected by \textit{sample forgetting issue}, where the model forgets the historically learned meta-training tasks while solely relying on support sets when adapting to new tasks. To overcome this predicament, we propose the \textbf{M}emory-based \textbf{C}ontrastive \textbf{M}eta-\textbf{L}earning (aka, MCML) method, including \textit{learn-from-the-memory} and \textit{adaption-from-the-memory} modules, which bridge the distribution gap between training episodes and between training and testing respectively. Specifically, the former uses an explicit memory bank to keep track of the label representations of previously trained episodes, with a contrastive constraint between the label representations in the current episode with the historical ones stored in the memory. In addition, the \emph{adaption-from-memory} mechanism is introduced to learn more accurate and robust representations based on the shift between the same labels embedded in the testing episodes and memory. Experimental results show that the MCML outperforms several state-of-the-art methods on both SNIPS and NER datasets and demonstrates strong scalability with consistent improvement when the number of shots gets greater.
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update. The normal meta-training strategy needs to differentiate through the inner-task adaptation procedure to optimize the meta-parameters. This leads to a constraint that the inner-task algorithms should be solved analytically. Under this constraint, only simple algorithms with analytical solutions can be applied as the inner-task algorithms, limiting the model expressiveness. To lift the limitation, we propose an adaptation-agnostic meta-training strategy. Following our proposed strategy, we can apply stronger algorithms (e.g., an ensemble of different types of algorithms) as the inner-task algorithm to achieve superior performance comparing with popular baselines. The source code is available at https://github.com/jiaxinchen666/AdaptationAgnosticMetaLearning.
In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more, the model can be ruined due to the domain shift between training data and testing data. Text recognition is a broadly studied field in computer vision and suffers from the same problems noted above due to the diversity of fonts and complicated backgrounds. In this paper, we focus on the text recognition problem and mainly make three contributions toward these problems. First, we collect a multi-source domain adaptation dataset for text recognition, including five different domains with over five million images, which is the first multi-domain text recognition dataset to our best knowledge. Secondly, we propose a new method called Meta Self-Learning, which combines the self-learning method with the meta-learning paradigm and achieves a better recognition result under the scene of multi-domain adaptation. Thirdly, extensive experiments are conducted on the dataset to provide a benchmark and also show the effectiveness of our method. The code of our work and dataset are available soon at https://bupt-ai-cz.github.io/Meta-SelfLearning/.
Practical recommender systems experience a cold-start problem when observed user-item interactions in the history are insufficient. Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples. Though with significant performance improvement, it commonly suffers from two critical issues: the non-compatibility with mainstream industrial deployment and the heavy computational burdens, both due to the inner-loop gradient operation. These two issues make them hard to be applied in practical recommender systems. To enjoy the benefits of meta learning framework and mitigate these problems, we propose a recommendation framework called Contextual Modulation Meta Learning (CMML). CMML is composed of fully feed-forward operations so it is computationally efficient and completely compatible with the mainstream industrial deployment. CMML consists of three components, including a context encoder that can generate context embedding to represent a specific task, a hybrid context generator that aggregates specific user-item features with task-level context, and a contextual modulation network, which can modulate the recommendation model to adapt effectively. We validate our approach on both scenario-specific and user-specific cold-start setting on various real-world datasets, showing CMML can achieve comparable or even better performance with gradient based methods yet with much higher computational efficiency and better interpretability.
Conditional Neural Processes (CNP; Garnelo et al., 2018) are an attractive family of meta-learning models which produce well-calibrated predictions, enable fast inference at test time, and are trainable via a simple maximum likelihood procedure. A limitation of CNPs is their inability to model dependencies in the outputs. This significantly hurts predictive performance and renders it impossible to draw coherent function samples, which limits the applicability of CNPs in down-stream applications and decision making. Neural Processes (NPs; Garnelo et al., 2018) attempt to alleviate this issue by using latent variables, relying on these to model output dependencies, but introduces difficulties stemming from approximate inference. One recent alternative (Bruinsma et al., 2021), which we refer to as the FullConvGNP, models dependencies in the predictions while still being trainable via exact maximum-likelihood. Unfortunately, the FullConvGNP relies on expensive 2D-dimensional convolutions, which limit its applicability to only one-dimensional data. In this work, we present an alternative way to model output dependencies which also lends itself maximum likelihood training but, unlike the FullConvGNP, can be scaled to two- and three-dimensional data. The proposed models exhibit good performance in synthetic experiments.
In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta Learning (OML) learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed one after another. Although it provides a sub-linear regret bound, such techniques completely ignore the importance of learning with fairness which is a significant hallmark of human intelligence. (2) Online Fairness-Aware Learning. This setting captures many classification problems for which fairness is a concern. But it aims to attain zero-shot generalization without any task-specific adaptation. This therefore limits the capability of a model to adapt onto newly arrived data. To overcome such issues and bridge the gap, in this paper for the first time we proposed a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention. The key part of FFML is to learn good priors of an online fair classification model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The problem is formulated in the form of a bi-level convex-concave optimization. Theoretic analysis provides sub-linear upper bounds for loss regret and for violation of cumulative fairness constraints. Our experiments demonstrate the versatility of FFML by applying it to classification on three real-world datasets and show substantial improvements over the best prior work on the tradeoff between fairness and classification accuracy