Model-agnostic Meta-learning Algorithm Research Articles

Fault Diagnosis Based on Tensor Computing and Meta-Learning for Smart Grid and Power Communication Network

Fault diagnosis (FD) is a critical challenge for the smart grid and the power communication network, especially when both heterogeneous networks are exponentially becoming enormous and complicated. Consequently, some conventional FD schemes based on labor seem inefficient, even disabled, because they usually cannot efficiently utilize multi-dimensional and heterogeneous big data from both networks. To deal with this challenging technical problem, a novel FD scheme based on tensor computing and meta-learning is proposed for the smart grid and the power communication network. In the proposed scheme, tensor computing is used to process tensor big data from both networks, and a new data fusion scheme is designed to complete and analyze the incomplete and sparse big data. Based on the fused data, a meta-learning approach is used to construct the FD scheme, especially when the target fault samples are inadequate and sparse. In meta-learning, the convolutional neural network is employed as a base learner to generate an FD training model, and the model-agnostic meta-learning algorithm is utilized to fine-tune and further train the pre-trained model. Simulation results and theoretical analysis indicate that the proposed DF scheme based on tensor computing can efficiently process sparse and heterogeneous big data from both networks. Furthermore, the meta-learning-based FD scheme provides an efficient way to diagnose faults with inadequate target samples. The proposed FD scheme based on tensor computing and meta-learning provides a novel solution to detect and analyze the potential faults for smart grid and power communication networks.

Robust and Generalized Physical Adversarial Attacks via Meta-GAN

Deep neural networks are known to be vulnerable to adversarial examples, where adding carefully crafted adversarial perturbations to the inputs can mislead the DNN model. However, it is challenging to generate effective adversarial examples in the physical world due to many uncontrollable physical dynamics, which pose security and safety threats in the real world. Current physical attack methods aim to generate robust physical adversarial examples by simulating all possible physical dynamics. If attacking a new image or a new DNN model, they require expensive manual efforts for simulating physical dynamics or considerable time for iteratively optimizing. To tackle these limitations, we propose a robust and generalized physical adversarial attack method with Meta-GAN (Meta-GAN Attack), which is able to not only generate robust physical adversarial examples, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images. First, we propose to craft robust physical adversarial examples with a generative attack model via simulating color and shape distortions. Second, we formulate the physical attack as a few-shot learning problem and design a novel class-agnostic and model-agnostic meta-learning algorithm to solve this problem. Extensive experiments on two benchmark datasets with four challenging experimental settings verify the superior robustness and generalization of our method by comparing to state-of-the-art physical attack methods. The source code is released at github.

A few-shot disease diagnosis decision making model based on meta-learning for general practice

BackgroundDiagnostic errors have become the biggest threat to the safety of patients in primary health care. General practitioners, as the “gatekeepers” of primary health care, have a responsibility to accurately diagnose patients. However, many general practitioners have insufficient knowledge and clinical experience in some diseases. Clinical decision making tools need to be developed to effectively improve the diagnostic process in primary health care. The long-tailed class distributions of medical datasets are challenging for many popular decision making models based on deep learning, which have difficulty predicting few-shot diseases. Meta-learning is a new strategy for solving few-shot problems. Methods and materialsIn this study, a few-shot disease diagnosis decision making model based on a model-agnostic meta-learning algorithm (FSDD-MAML) is proposed. The MAML algorithm is applied in a knowledge graph-based disease diagnosis model to find the optimal model parameters. Moreover, FSDD-MAML can learn learning rates for all modules of the knowledge graph-based disease diagnosis model. For n-way, k-shot learning tasks, the inner loop of FSDD-MAML performs multiple gradient update steps to learn internal features in disease classification tasks using n×k examples, and the outer loop of FSDD-MAML optimizes the meta-objective to find the associated optimal parameters and learning rates. FSDD-MAML is compared with the original knowledge graph-based disease diagnosis model and other meta-learning algorithms based on an abdominal disease dataset. ResultMeta-learning algorithms can greatly improve the performance of models in top-1 evaluation compared with top-3, top-5, and top-10 evaluations. The proposed decision making model FSDD-MAML outperforms all the other models, with a precision@1 of 90.02 %. We achieve state-of-the-art performance in the diagnosis of all diseases, and the prediction performance for few-shot diseases is greatly improved. For the two groups with the fewest examples of diseases, FSDD-MAML achieves relative increases in precision@1 of 29.13 % and 21.63 % compared with the original knowledge graph-based disease diagnosis model. In addition, we analyze the reasoning process of several few-shot disease predictions and provide an explanation for the results. ConclusionThe decision making model based on meta-learning proposed in this paper can support the rapid diagnosis of diseases in general practice and is especially capable of helping general practitioners diagnose few-shot diseases. This study is of profound significance for the exploration and application of meta-learning to few-shot disease assessment in general practice.

Battling with the low-resource condition for snore sound recognition: introducing a meta-learning strategy

Snoring affects 57 % of men, 40 % of women, and 27 % of children in the USA. Besides, snoring is highly correlated with obstructive sleep apnoea (OSA), which is characterised by loud and frequent snoring. OSA is also closely associated with various life-threatening diseases such as sudden cardiac arrest and is regarded as a grave medical ailment. Preliminary studies have shown that in the USA, OSA affects over 34 % of men and 14 % of women. In recent years, polysomnography has increasingly been used to diagnose OSA. However, due to its drawbacks such as being time-consuming and costly, intelligent audio analysis of snoring has emerged as an alternative method. Considering the higher demand for identifying the excitation location of snoring in clinical practice, we utilised the Munich-Passau Snore Sound Corpus (MPSSC) snoring database which classifies the snoring excitation location into four categories. Nonetheless, the problem of small samples remains in the MPSSC database due to factors such as privacy concerns and difficulties in accurate labelling. In fact, accurately labelled medical data that can be used for machine learning is often scarce, especially for rare diseases. In view of this, Model-Agnostic Meta-Learning (MAML), a small sample method based on meta-learning, is used to classify snore signals with less resources in this work. The experimental results indicate that even when using only the ESC-50 dataset (non-snoring sound signals) as the data for meta-training, we are able to achieve an unweighted average recall of 60.2 % on the test dataset after fine-tuning on just 36 instances of snoring from the development part of the MPSSC dataset. While our results only exceed the baseline by 4.4 %, they still demonstrate that even with fine-tuning on a few instances of snoring, our model can outperform the baseline. This implies that the MAML algorithm can effectively tackle the low-resource problem even with limited data resources.

MODEL-AGNOSTIC META-LEARNING FOR RESILIENCE OPTIMIZATION OF ARTIFICIAL INTELLIGENCE SYSTEM

Context. The problem of optimizing the resilience of artificial intelligence systems to destructive disturbances has not yet been fully solved and is quite relevant for safety-critical applications. The task of optimizing the resilience of an artificial intelligence system to disturbing influences is a high-level task in relation to efficiency optimization, which determines the prospects of using the ideas and methods of meta-learning to solve it. The object of current research is the process of meta-learning aimed at optimizing the resilience of an artificial intelligence system to destructive disturbances. The subjects of the study are architectural add-ons and the meta-learning method which optimize resilience to adversarial attacks, fault injection, and task changes.
 Objective. Stated research goal is to develop an effective meta-learning method for optimizing the resilience of an artificial intelligence system to destructive disturbances.
 Method. The resilience optimization is implemented by combining the ideas and methods of adversarial learning, fault-tolerant learning, model-agnostic meta-learning, few-shot learning, gradient optimization methods, and probabilistic gradient approximation strategies. The choice of architectural add-ons is based on parameter-efficient knowledge transfer designed to save resources and avoid the problem of catastrophic forgetting.
 Results. A model-agnostic meta-learning method for optimizing the resilience of artificial intelligence systems based on gradient meta-updates or meta-updates using an evolutionary strategy has been developed. This method involves the use of tuner and metatuner blocks that perform parallel correction of the building blocks of a original deep neural network. The ability of the proposed approach to increase the efficiency of perturbation absorption and increase the integral resilience indicator of the artificial intelligence system is experimentally tested on the example of the image classification task. The experiments were conducted on a model with the ResNet-18 architecture, with an add-on in the form of tuners and meta-tuners with the Conv-Adapter architecture. In this case, CIFAR-10 is used as a base set on which the model was trained, and CIFAR-100 is used as a set for generating samples on which adaptation is performed using a few-shot learning scenarios. We compare the resilience of the artificial intelligence system after pre-training tuners and meta-tuners using the adversarial learning algorithm, the fault-tolerant learning algorithm, the conventional model-agnostic meta-learning algorithm, and the proposed meta-learning method for optimizing resilience. Also, the meta-learning algorithms with meta-gradient updating and meta-updating based on the evolutionary strategy are compared on the basis of the integral resilience indicator.
 Conclusions. It has been experimentally confirmed that the proposed method provides a better resilience to random bit-flip injection compared to fault injection training by an average of 5%. Also, the proposed method provides a better resilience to Ladversarial evasion attacks compared to adversarial training by an average of 4.8%. In addition, an average 4.8% increase in the resilience to task changes is demonstrated compared to conventional fine-tuning of tuners. Moreover, meta-learning with an evolutionary strategy provides, on average, higher values of the resilience indicator. On the downside, this meta-learning method requires more iterations.

Meta-learning for few-shot time series forecasting

Time series forecasting (TSF) is significant for many applications, therefore the exploration and study for this problem has been proceeding. With the advances of computing power, deep neural networks (DNNs) have shown powerful performance on many machine learning tasks when considerable amounts of data can be used. However, sufficient data may be unavailable in some scenarios, which leads to performance degradation or even not working of DNN-based models. In this paper, we focus on few-shot time series forecasting task and propose to employ meta-learning to alleviate the problems caused by insufficient training data. Therefore, we propose a meta-learning-based prediction mechanism for few-shot time series forecasting task, which mainly consists of meta-training and meta-testing. The meta-training phase uses first-order model-agnostic meta-learning algorithm (MAML) as a core component to conduct cross-task training, and thus our method also inherits the advantages of the MAML, i.e., model-agnostic, in the sense that our method is compatible with any model trained with gradient descent. In the meta-testing phase, the DNN-based models are fine-tuned by the small number of time series data from an unseen task in the meta-training phase. We design two groups of comparison models to validate the effectiveness of our method. The first group, as the baseline models, is trained directly on specific time series dataset from target task. The second group, as comparison models, is trained by our proposed method. Also, we conduct data sensitivity study to validate the robustness of our method. The experimental results indicate the second group models outperform the first in different degrees in terms of prediction accuracy and convergence speed, and our method has strong robustness for forecast horizons and data scales.

Meta-learning for fake news detection surrounding the Syrian war

SummaryIn this article, we pursue the automatic detection of fake news reporting on the Syrian war using machine learning and meta-learning. The proposed approach is based on a suite of features that include a given article's linguistic style; its level of subjectivity, sensationalism, and sectarianism; the strength of its attribution; and its consistency with other news articles from the same “media camp”. To train our models, we use FA-KES, a fake news dataset about the Syrian war. A suite of basic machine learning models is explored, as well as the model-agnostic meta-learning algorithm (MAML) suitable for few-shot learning, using datasets of a modest size. Feature-importance analysis confirms that the collected features specific to the Syrian war are indeed very important predictors for the output label. The meta-learning model achieves the best performance, improving upon the baseline approaches that are trained exclusively on text features in FA-KES.

Meta-Learning for Fake News Detection Surrounding the Syrian War

In this manuscript, we pursue the automatic detection of fake news reporting on the Syrian war using machine learning and meta-learning. Our model is based on a suite of features that include a given article's linguistic style, its level of subjectivity, sensationalism and sectarianism, the strength of its attribution, as well as its consistency with other news articles from the same ``media camp'' and reporting on the same single large-scale event detected from a timeline of the Syrian war. To train our model, we use FA-KES, a fake news dataset about the Syrian war, consisting of 804 articles roughly balanced between true and fake . We explore a suite of basic machine learning models as well as the model-agnostic meta-learning algorithm (MAML) suitable for few-shot learning, using datasets of a modest size. Our feature importance analysis confirms that our collection of features specific to the Syrian war are indeed very important predictors for the output label. Our meta-learning model achieves the best performance improving upon the baseline approaches that are trained exclusively on text features in FA-KES in about 20% inaccuracy, 15% in F1-measure, and 30% in AUC. It also achieves more robust probabilistic outcomes and higher top k precision and recall than the vanilla machine learning models.

Small sample classification of hyperspectral image using model-agnostic meta-learning algorithm and convolutional neural network

ABSTRACT The difficulties of obtaining sufficient high-quality labelled samples have always been one of the important factors hindering the practical application of hyperspectral images (HSI) classification. The regular deep learning models only attempt to mine the discriminant and informative features in the target HSI. Therefore, the satisfactory results cannot be obtained with only a few labelled samples because their huge parameter space cannot be fully trained. To this end, a simple and effective framework is proposed utilizing the idea of meta-learning to improve HSI classification performance under the condition of small sample. Specifically, we design a simple model by stacking convolutional blocks, and introduce a model-agnostic meta-learning algorithm (MAML) to enable the model to implement meta-optimization on vast different tasks. The MAML algorithm can enable the model to acquire the more general-purpose representations, so as to adapt quickly to new tasks with only a few labelled samples and a small number of gradient update steps. To improve the practical value of the research, two kinds of classification scenarios, cross-data small sample classification on the same HSI and cross-scene small sample classification between different HSI, are designed for experiments. The results on three public HSI demonstrate that our method outperform the state-of-the-art methods in both scenarios. In addition, the proposed method, actually an optimization-based meta-learning method, provides a new idea for HSI small sample classification.

Learning to Reason in Round-Based Games: Multi-Task Sequence Generation for Purchasing Decision Making in First-Person Shooters

Sequential reasoning is a complex human ability, with extensive previous research focusing on gaming AI in a single continuous game, round-based decision makings extending to a sequence of games remain less explored. Counter-Strike: Global Offensive (CS:GO), as a round-based game with abundant expert demonstrations, provides an excellent environment for multi-player round-based sequential reasoning. In this work, we propose a Sequence Reasoner with Round Attribute Encoder and Multi-Task Decoder to interpret the strategies behind the round-based purchasing decisions. We adopt few-shot learning to sample multiple rounds in a match, and modified model agnostic meta-learning algorithm Reptile for the meta-learning loop. We formulate each round as a multi-task sequence generation problem. Our state representations combine action encoder, team encoder, player features, round attribute encoder, and economy encoders to help our agent learn to reason under this specific multi-player round-based scenario. A complete ablation study and comparison with the greedy approach certify the effectiveness of our model. Our research will open doors for interpretable AI for understanding episodic and long-term purchasing strategies beyond the gaming community.

Meta weight learning via model-agnostic meta-learning

While meta learning approaches have achieved remarkable success, obtaining a stable and unbiased meta-learner remains a significant challenge, since the initial model of a meta-learner could be too biased towards existing tasks to adapt to new tasks. In order to avoid a biased meta-learner and improve its generalizability, this paper proposes a generic meta learning method that aims to learn an unbiased meta-learner towards a variety of tasks before its initial model is adapted to unseen tasks. Specifically, this paper presents a meta weight learning method for minimizing the inequality of performance across different training tasks. An end-to-end training approach is introduced for the proposed algorithm that allows for effectively learning weight and initializing the network model. Alternatively, a variety of measurement methods of weight is also designed to test the effectiveness of different weight learning methods on the improvement of model-agnostic meta-learning algorithm. The simulation results show that the proposed meta weight learning method not only outperforms state-of-the-art meta learning algorithms, but also is superior to other manually designed measurement methods of weight on discrete and continuous control problems.

Ensemble Meta-Learning for Few-Shot Soot Density Recognition

In each petrochemical plant around the world, the flare stack as a requisite facility produces a large amount of soot due to the incomplete combustion of flare gas, and this strongly endangers air quality and human health. Despite severe damages, the abovementioned abnormal conditions rarely occur, and, thus, only few-shot samples are available. To address such difficulty, in this article, we design an image-based flare soot density recognition network (FSDR-Net) via a new ensemble meta-learning technology. More particularly, we first train a deep convolutional neural network (CNN) by applying the model-agnostic meta-learning algorithm on a variety of learning tasks that are relevant to the flare soot recognition so as to obtain the general-purpose optimized initial parameters (GOIP). Second, for the new task of recognizing the flare soot density via only few-shot instances, a new ensemble is developed to selectively aggregate several predictions that are generated based on a wide range of learning rates and a small number of gradient steps. Results of experiments conducted on the density recognition of flare soot corroborate the superiority of our proposed FSDR-Net as compared with the popular and state-of-the-art deep CNNs.