Target Task Research Articles

Ensemble of Domain Adaptation-Based Knowledge Transfer for Evolutionary Multitasking

Recently, a number of domain adaptation methods have been proposed for knowledge transfer in evolutionary multitasking (EMT). However, the learnt mappings in these methods often have unique biases in representing the connection between source and target tasks. Few studies have paid attention to the complementarity of different mappings in knowledge transfer. To fill this research gap, this paper proposes an ensemble method to combine multiple domain adaptation methods for knowledge transfer in EMT by considering the efficacy and diversity of these methods. First, a hierarchical clustering method is used to divide the population of each task into multiple clusters. Then, when two parental solutions are selected for knowledge transfer across tasks, the solutions within the same cluster are checked. In particular, if none of these solutions has been transferred before, the efficacy of domain adaptation methods is considered first by using roulette wheel selection based on the corresponding performance improvements in the evolutionary optimization process. Otherwise, the diversity of domain adaptation methods is emphasized by randomly selecting one of the domain adaptation methods for knowledge transfer. The effectiveness of our proposed ensemble method is validated by embedding it into existing state-of-the-art EMT algorithms, and the experimental results show that our algorithm outperforms several recently proposed EMT algorithms on most cases of two multitasking benchmark suites and one practical case.

Multidomain Adaptation With Sample and Source Distillation.

Unsupervised multidomain adaptation attracts increasing attention as it delivers richer information when tackling a target task from an unlabeled target domain by leveraging the knowledge attained from labeled source domains. However, it is the quality of training samples, not just the quantity, that influences transfer performance. In this article, we propose a multidomain adaptation method with sample and source distillation (SSD), which develops a two-step selective strategy to distill source samples and define the importance of source domains. To distill samples, the pseudo-labeled target domain is constructed to learn a series of category classifiers to identify transfer and inefficient source samples. To rank domains, the agreements of accepting a target sample as the insider of source domains are estimated by constructing a domain discriminator based on selected transfer source samples. Using the selected samples and ranked domains, transfer from source domains to the target domain is achieved by adapting multilevel distributions in a latent feature space. Furthermore, to explore more usable target information which is expected to enhance the performance across domains of source predictors, an enhancement mechanism is built by matching selected pseudo-labeled and unlabeled target samples. The degrees of acceptance learned by the domain discriminator are finally employed as source merging weights to predict the target task. Superiority of the proposed SSD is validated on real-world visual classification tasks.

Minimizing Parameter Overhead in Self-Supervised Models for Target Task

Minimizing Parameter Overhead in Self-Supervised Models for Target Task

Prediction and simulation of PEEP setting effects with machine learning models

ObjectiveTo establish a new machine learning-based method to adjust positive end-expiratory pressure (PEEP) using only already routinely measured data. DesignRetrospective observational study. SettingIntensive care unit (ICU). Patients or participants51811 mechanically ventilated patients in multiple ICUs in the USA (data from MIMIC-III and eICU databases). InterventionsNo interventions. Main variables of interestSuccess parameters of ventilation (arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance) ResultsThe multi-tasking neural network model performed significantly best for all target tasks in the primary test set. The model predicts arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance about 45 min into the future with mean absolute percentage errors of about 21.7%, 10.0% and 15.8%, respectively. The proposed use of the model was demonstrated in case scenarios, where we simulated possible effects of PEEP adjustments for individual cases. ConclusionsOur study implies that machine learning approach to PEEP titration is a promising new method which comes with no extra cost once the infrastructure is in place. Availability of databases with most recent ICU patient data is crucial for the refinement of prediction performance.

Human error probability evaluation based on reference task using intuitionistic fuzzy theory

Human Reliability Analysis (HRA) is a critical issue for addressing human error in system reliability. There are numerous tasks for which human factors-related data are not available, rendering expert knowledge the only basis for assessing such tasks. However, the knowledge obtained from experts is subject to ambiguity and vagueness, which affects the usability of the assessment results. To overcome this challenge, in this paper a reference task based HRA method is proposed and the intuitionistic fuzzy set (IFS) is adopted because of its advantage of being able to handle ambiguous information. Firstly, to analyze the human error probability (HEP) of the target task, a reference task-based human error analysis model is introduced. Two solutions are provided: calculating the performance shaping factors (PSFs) distance between the reference task and the target task and establishing a quantitative relationship between PSFs and HEP. Secondly, the PSFs evaluation and inference methods based on triangular intuitionistic fuzzy numbers (TIFNs) are developed. Finally, the effectiveness and consistency of the two solutions of TIFN-HRA are demonstrated through a spaceflight refueling mission analysis. The distances between the results of the two solutions and the expert linguistic are compared and both results have the shortest distance to “Low”. However, solution I is simpler and the result is clearer.

Zero-Shot Task Adaptation with Relevant Feature Information

We propose a method to learn prediction models such as classifiers for unseen target tasks where labeled and unlabeled data are absent but a few relevant input features for solving the tasks are given. Although machine learning requires data for training, data are often difficult to collect in practice. On the other hand, for many applications, a few relevant features would be more easily obtained. Although zero-shot learning or zero-shot domain adaptation use external knowledge to adapt to unseen classes or tasks without data, relevant features have not been used in existing studies. The proposed method improves the generalization performance on the target tasks, where there are no data but a few relevant features are given, by meta-learning from labeled data in related tasks. In the meta-learning phase, it is essential to simulate test phases on target tasks where prediction model learning is required without data. To this end, our neural network-based prediction model is meta-learned such that it correctly responds to perturbations of the relevant features on randomly generated synthetic data. By this modeling, the prediction model can explicitly learn the discriminability of the relevant features without real target data. When unlabeled training data are available in the target tasks, the proposed method can incorporate such data to boost the performance in a unified framework. Our experiments demonstrate that the proposed method outperforms various existing methods with four real-world datasets.

H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer

Multi-source transfer learning is an effective solution to data scarcity by utilizing multiple source tasks for the learning of the target task. However, access to source data and model details is limited in the era of commercial models, giving rise to the setting of multi-source-free (MSF) transfer learning that aims to leverage source domain knowledge without such access. As a newly defined problem paradigm, MSF transfer learning remains largely underexplored and not clearly formulated. In this work, we adopt an information theoretic perspective on it and propose a framework named H-ensemble, which dynamically learns the optimal linear combination, or ensemble, of source models for the target task, using a generalization of maximal correlation regression. The ensemble weights are optimized by maximizing an information theoretic metric for transferability. Compared to previous works, H-ensemble is characterized by: 1) its adaptability to a novel and realistic MSF setting for few-shot target tasks, 2) theoretical reliability, 3) a lightweight structure easy to interpret and adapt. Our method is empirically validated by ablation studies, along with extensive comparative analysis with other task ensemble and transfer learning methods. We show that the H-ensemble can successfully learn the optimal task ensemble, as well as outperform prior arts.

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks, especially unfamiliar ones. However, current methods for generative script learning rely heavily on well-structured preceding steps described in text and/or images or are limited to a certain domain, resulting in a disparity with real-world user scenarios. To address these limitations, we present a new benchmark challenge – MULTISCRIPT, with two new tasks on task-oriented multimodal script learning: (1) multimodal script generation, and (2) subsequent step prediction. For both tasks, the input consists of a target task name and a video illustrating what has been done to complete the target task, and the expected output is (1) a sequence of structured step descriptions in text based on the demonstration video, and (2) a single text description for the subsequent step, respectively. Built from WikiHow, MULTISCRIPT covers multimodal scripts in videos and text descriptions for over 6,655 human everyday tasks across 19 diverse domains. To establish baseline performance on MULTISCRIPT, we propose two knowledge-guided multimodal generative frameworks that incorporate the task-related knowledge prompted from large language models such as Vicuna. Experimental results show that our proposed approaches significantly improve over the competitive baselines.

Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following

In this paper, we present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. TAPP is different from canonical prompts for LLMs in that it is a fixed prompt prepended to the beginning of every input regardless of the target task for zero-shot generalization. We observe that both base LLMs (i.e. not fine-tuned to follow instructions) and instruction-tuned models benefit from TAPP, resulting in 34.58% and 12.26% improvement on average, respectively. This implies that the instruction-following ability of LLMs can be improved during inference time with a fixed prompt constructed with simple heuristics. We hypothesize that TAPP assists language models to better estimate the output distribution by focusing more on the instruction of the target task during inference. In other words, such ability does not seem to be sufficiently activated in not only base LLMs but also many instruction-fine-tuned LLMs.

Few-Shot Learning via Repurposing Ensemble of Black-Box Models

This paper investigates the problem of exploiting existing solution models of previous tasks to address a related target task with limited training data. Existing approaches addressing this problem often require access to the internal parameterization of the existing solution models and possibly their training data, which is not possible in many practical settings. To relax this requirement, We approach this problem from a new perspective of black-box re-purposing, which augments the target inputs and leverages their corresponding outputs generated by existing black-box APIs into a feature ensemble. We hypothesize that such feature ensemble can be learned to incorporate and encode relevant black-box knowledge into the feature representation of target data, which will compensate for their scarcity. This hypothesis is confirmed via the reported successes of our proposed black-box ensemble in solving multiple few-shot learning tasks derived from various benchmark datasets. All reported results show consistently that the set of heterogeneous black-box solutions of previous tasks can indeed be reused and combined effectively to solve a reasonably related target task without requiring access to a large training dataset. This is the first step towards enabling new possibilities to further supplement existing techniques in transfer or meta learning with black-box knowledge.

Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills

Offline meta-reinforcement learning (meta-RL) methods, which adapt to unseen target tasks with prior experience, are essential in robot control tasks. Current methods typically utilize task contexts and skills as prior experience, where task contexts are related to the information within each task and skills represent a set of temporally extended actions for solving subtasks. However, these methods still suffer from limited performance when adapting to unseen target tasks, mainly because the learned prior experience lacks generalization, i.e., they are unable to extract effective prior experience from meta-training tasks by exploration and learning of continuous latent spaces. We propose a framework called decoupled meta-reinforcement learning (DCMRL), which (1) contrastively restricts the learning of task contexts through pulling in similar task contexts within the same task and pushing away different task contexts of different tasks, and (2) utilizes a Gaussian quantization variational autoencoder (GQ-VAE) for clustering the Gaussian distributions of the task contexts and skills respectively, and decoupling the exploration and learning processes of their spaces. These cluster centers which serve as representative and discrete distributions of task context and skill are stored in task context codebook and skill codebook, respectively. DCMRL can acquire generalizable prior experience and achieve effective adaptation to unseen target tasks during the meta-testing phase. Experiments in the navigation and robot manipulation continuous control tasks show that DCMRL is more effective than previous meta-RL methods with more generalizable prior experience.

Structured Probabilistic Coding

This paper presents a new supervised representation learning framework, namely structured probabilistic coding (SPC), to learn compact and informative representations from input related to the target task. SPC is an encoder-only probabilistic coding technology with a structured regularization from the target space. It can enhance the generalization ability of pre-trained language models for better language understanding. Specifically, our probabilistic coding simultaneously performs information encoding and task prediction in one module to more fully utilize the effective information from input data. It uses variational inference in the output space to reduce randomness and uncertainty. Besides, to better control the learning process of probabilistic representations, a structured regularization is proposed to promote uniformity across classes in the latent space. With the regularization term, SPC can preserve the Gaussian structure of the latent code and achieve better coverage of the hidden space with class uniformly. Experimental results on 12 natural language understanding tasks demonstrate that our SPC effectively improves the performance of pre-trained language models for classification and regression. Extensive experiments show that SPC can enhance the generalization capability, robustness to label noise, and clustering quality of output representations.

Systematic analysis of the functional features of the information and analytical system of the professional development of the communicative culture of documents

The need for systematic analysis of information and analytical systems in the fields of knowledge education/pedagogical sciences, socio-behavioral sciences and culture and art has been updated. The conceptual-categorical apparatus of the system analysis of the functionality of the information-analytical system of the professional development of the communicative culture of document editors is singled out. The concept of "informational and analytical system" has been clarified, the definition of "informational and analytical system of higher education institutions" has been specified. The goal of formation and target tasks of the information and analytical system of higher education institutions, its structure and factors of regulation are disclosed, the structural components of the system are established. The methodical apparatus of the system approach in information-analytical activity and the subject area of research of the system analysis of the information-analytical system of the professional development of document editors have been clarified. The classification features of system-forming characteristics, which are the subject of system analysis, are singled out. A systematic approach was applied to determine the functional structure of the system. Management functions have been updated, classification features of management functionality have been highlighted. In the course of the system analysis, the functional features of the information- analytical system of professional training and development of the communicative culture of document editors were classified, namely the functions: law-enforcing legal protection of social guarantees of the national and global dimension; political- administrative by types and types of policies of different levels of management; socio-economic connection to ensure the effectiveness of the policy of sustainable development; cultural and artistic academic culture; supervisory sphere of technical regulation; serving from the service of legal and social protection of participants in educational and research processes.

Transfer learning for metamaterial design and simulation

Abstract We demonstrate transfer learning as a tool to improve the efficacy of training deep learning models based on residual neural networks (ResNets). Specifically, we examine its use for study of multi-scale electrically large metasurface arrays under open boundary conditions in electromagnetic metamaterials. Our aim is to assess the efficiency of transfer learning across a range of problem domains that vary in their resemblance to the original base problem for which the ResNet model was initially trained. We use a quasi-analytical discrete dipole approximation (DDA) method to simulate electrically large metasurface arrays to obtain ground truth data for training and testing of our deep neural network. Our approach can save significant time for examining novel metasurface designs by harnessing the power of transfer learning, as it effectively mitigates the pervasive data bottleneck issue commonly encountered in deep learning. We demonstrate that for the best case when the transfer task is sufficiently similar to the target task, a new task can be effectively trained using only a few data points yet still achieve a test mean absolute relative error of 3 % with a pre-trained neural network, realizing data reduction by a factor of 1000.

FTSDC: A novel federated transfer learning strategy for bearing cross-machine fault diagnosis based on dual-correction training

In recent years, although traditional intelligent fault diagnosis methods have achieved satisfactory development in transfer learning tasks, the sample information that the single client can generally provide is extremely limited in real industrial scenarios. And the private data needs to be guaranteed not to leave the local storage during the application process, which leads to obstacles for fault diagnosis methods to solve cross-device and cross-scenario client transfer tasks. Therefore, a novel federated transfer learning strategy based on dual-correction training (FTSDC) is proposed, which enables fault diagnosis for multi-device tasks without target domain samples to participate in model training. The dual correction training of source client is proposed to enhance the local network’s generality, which involves two links: The multiple-functions correction model hyperparameters link and the transition training correction network attention area link. Multiple sets of optimization functions are introduced into local network training to reduce the covariate drift phenomenon caused by domain discrepancies. And the local model fine-tunes the parameters of the trained network through the transition dataset to correct attention areas. Furthermore, The central server evaluates each source client model according to the contribution of the local model to the transfer strategy, and the local model parameters are cumulatively optimized by referring to the diagnosic experience of the global model. It is worth noting that the trained local model can still demonstrate commendable performance even when faced with more complex scenarios. Finally, the proposed scheme was rigorously assessed against diverse federated learning methods across various task settings during the experimental session. The results confirmed the effectiveness of the proposed scheme in safeguarding the data privacy of each client while concurrently enhancing the diagnostic accuracy of the target task.

Self-supervised learning for medical image data with anatomy-oriented imaging planes

Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is crucial to the success of transfer learning. Various pretext tasks have been proposed to utilize properties of medical image data (e.g., three dimensionality), which are more relevant to medical image analysis than generic ones for natural images. However, previous work rarely paid attention to data with anatomy-oriented imaging planes, e.g., standard cardiac magnetic resonance imaging views. As these imaging planes are defined according to the anatomy of the imaged organ, pretext tasks effectively exploiting this information can pretrain the networks to gain knowledge on the organ of interest. In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes. The first is to learn the relative orientation between the imaging planes and implemented as regressing their intersecting lines. The second exploits parallel imaging planes to regress their relative slice locations within a stack. Both pretext tasks are conceptually straightforward and easy to implement, and can be combined in multitask learning for better representation learning. Thorough experiments on two anatomical structures (heart and knee) and representative target tasks (semantic segmentation and classification) demonstrate that the proposed pretext tasks are effective in pretraining deep networks for remarkably boosted performance on the target tasks, and superior to other recent approaches.

Transfer learning with high dimensional composite quantile regression

Transfer learning has gained wide popularity due to its ability to enhance the performance of target tasks by utilizing external information sources. Despite this, current transfer learning methods often struggle to consistently and effectively handle heterogeneous and/or heavy tail data. To address this issue, we propose a robust transfer learning method based on the composite quantile regression model that can adapt to a variety of data types and integrate multiple quantile information. Additionally, this method can handle situations where the error term variance is infinite. A challenging scenario in transfer learning is that the transferable data set is unknown, so we design two detection algorithms to correctly identify valid transferable data sets. Through numerical simulations and empirical analysis, we verify the good performance of the above algorithms based on the high-dimensional composite quantile regression model.

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Multimodal remote sensing data classification can enhance a model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks has become the focus of researchers. Inspired by the human feedback learning mechanism, causal reasoning mechanism, and knowledge induction mechanism, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposes causal meta-reinforcement learning (CMRL). First, based on the feedback learning mechanism, we overcame the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we helped the agents understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information.Second, based on the causal inference mechanism, we designed causal distribution prediction actions, classification rewards, and causal intervention rewards, capturing pure causal factors in multimodal data and preventing false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets showed that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

Efficient Structured Prediction with Transformer Encoders

Finetuning is a useful method for adapting Transformer-based text encoders to new tasks but can be computationally expensive for structured prediction tasks that require tuning at the token level. Furthermore, finetuning is inherently inefficient in updating all base model parameters, which prevents parameter sharing across tasks. To address these issues, we propose a method for efficient task adaptation of frozen Transformer encoders based on the local contribution of their intermediate layers to token representations. Our adapter uses a novel attention mechanism to aggregate intermediate layers and tailor the resulting representations to a target task. Experiments on several structured prediction tasks demonstrate that our method outperforms previous approaches, retaining over 99% of the finetuning performance at a fraction of the training cost. Our proposed method offers an efficient solution for adapting frozen Transformer encoders to new tasks, improving performance and enabling parameter sharing across different tasks.

Artificial Intelligence Methods in Automated Unmanned Aerial Vehicles Control Systems

One of the main problems in ensuring the unmanned aerial systems (UAS) safety and control performance indicators is the operational analysis organization of heterogeneous data coming from on-board sensors and the formation of adequate recommendations and decisions on their basis of flight missions implementation. In recent years, there have been many research papers devoted to solving this problem using artificial intelligence (AI) methods. The article discusses AI methods for using in tasks related to UAS. We have described the sources of information to generate the data necessary for the application of AI methods. We have classified typical tasks of computer vision and navigation systems for solving using AI methods. We have analyzed the generally accepted classification of AI methods within the scope of the research subject. At the same time, special attention is paid to the features of AI methods that allow solving many well-known problems of recognition, approximation, optimization for UAS target and navigation tasks realization and effective operator support. In particular, we have considered neural networks, decision trees, support vector machines, k-nearest neighbors, genetic, ant colony algorithms, artificial immune systems. Currently, the hardware allows integrating complex algorithms based on these methods on board and widely using them in flight missions. The results of the study conducted as part of the review are illustrated by examples from the scientific publications.