Techniques for transferring host-pathogen protein interactions knowledge to new tasks.

Domain- and task-specific transfer learning for medical segmentation tasks

What matters in a transferable neural network model for relation classification in the biomedical domain?

Neural transfer learning for assigning diagnosis codes to EMRs

Transfer learning refers to the transfer of knowledge or information from a relevant source task to a target task. However, most existing works assume both tasks are sampled from a stationary task distribution, thereby leading to the sub-optimal performance for dynamic tasks drawn from a non-stationary task distribution in real scenarios. To bridge this gap, in this paper, we study a more realistic and challenging transfer learning setting with dynamic tasks, i.e., source and target tasks are continuously evolving over time. We theoretically show that the expected error on the dynamic target task can be tightly bounded in terms of source knowledge and consecutive distribution discrepancy across tasks. This result motivates us to propose a generic meta-learning framework L2E for modeling the knowledge transferability on dynamic tasks. It is centered around a task-guided meta-learning problem with a group of meta-pairs of tasks, based on which we are able to learn the prior model initialization for fast adaptation on the newest target task. L2E enjoys the following properties: (1) effective knowledge transferability across dynamic tasks; (2) fast adaptation to the new target task; (3) mitigation of catastrophic forgetting on historical target tasks; and (4) flexibility in incorporating any existing static transfer learning algorithms. Extensive experiments on various image data sets demonstrate the effectiveness of the proposed L2E framework.

Transfer learning enables machine learning system to use previously acquired knowledge from source task on target task. Source task and target task should be correlated. Successful transfer learning would improve system performance on target task especially when target data is small. In this paper, the source task is Indonesian part-of-speech (POS) tagging system and the target task is Indonesian named entity recognition (NER) tagging system. A bidirectional gated recurrent unit and conditional random field (GRU-CRF) sequence labeller is crafted as the model for the feature representation transfer to be applied. We compared F1 evaluation results between system that used transfer and system that did not use transfer and saw an improvement around 0.02 on the transferred model when 100% training data was used and around 0.15 when 1% training data was used.

Pathogenic microorganisms exploit host cellular mechanisms and evade host defense mechanisms through molecular pathogen-host interactions (PHIs). Therefore, comprehensive analysis of these PHI networks should be an initial step for developing effective therapeutics against infectious diseases. Computational prediction of PHI data is gaining increasing demand because of scarcity of experimental data. Prediction of protein-protein interactions (PPIs) within PHI systems can be formulated as a classification problem, which requires the knowledge of non-interacting protein pairs. This is a restricting requirement since we lack datasets that report non-interacting protein pairs. In this study, we formulated the "computational prediction of PHI data" problem using kernel embedding of heterogeneous data. This eliminates the abovementioned requirement and enables us to predict new interactions without randomly labeling protein pairs as non-interacting. Domain-domain associations are used to filter the predicted results leading to 175 novel PHIs between 170 human proteins and 105 viral proteins. To compare our results with the state-of-the-art studies that use a binary classification formulation, we modified our settings to consider the same formulation. Detailed evaluations are conducted and our results provide more than 10 percent improvements for accuracy and AUC (area under the receiving operating curve) results in comparison with state-of-the-art methods.

Transfer learning is a method for improving generalization performance by training a model for a different task first and then additionally training the pre-learned weights for the target task. However, transferability—the ease with which source task can be effectively transferred to which target task—is often unknown. Existing works proposed methods of measuring the transferability between classification tasks using images and discrete labels, but it cannot be applied to regression tasks. In this work, we investigate transferability among classification and regression tasks, and propose a method for predicting transferability by extending the optimal transport theory. Our transferability prediction model also can be applied to subjective tasks (e.g., aesthetics and memorability), which are usually regression tasks. We show that the appropriate source (pre-training) tasks can be predicted for the chosen target task without conducting actual pre-training and transferring trials. Experimental results demonstrated high prediction accuracy (correlation coefficient of ρ=0.791\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho =0.791$$\\end{document}) and a speed improvement of approximately 300 times compared with the above-mentioned greedy approach.

Transfer learning in reinforcement learning has been an active area of research over the past decade. In transfer learning, training on a source task is leveraged to speed up or otherwise improve learning on a target task. This paper presents the more ambitious problem of curriculum learning in reinforcement learning, in which the goal is to design a sequence of source tasks for an agent to train on, such that final performance or learning speed is improved. We take the position that each stage of such a curriculum should be tailored to the current ability of the agent in order to promote learning new behaviors. Thus, as a first step towards creating a curriculum, the trainer must be able to create novel, agent-specific source tasks. We explore how such a space of useful tasks can be created using a parameterized model of the domain and observed trajectories on the target task. We experimentally show that these methods can be used to form components of a curriculum and that such a curriculum can be used successfully for transfer learning in 2 challenging multiagent reinforcement learning domains.

Given its demonstrated ability in analyzing and revealing patterns underlying data, Deep Learning (DL) has been increasingly investigated to complement physics-based models in various aspects of smart manufacturing, such as machine condition monitoring and fault diagnosis, complex manufacturing process modeling, and quality inspection. However, successful implementation of DL techniques relies greatly on the amount, variety, and veracity of data for robust network training. Also, the distributions of data used for network training and application should be identical to avoid the internal covariance shift problem that reduces the network performance applicability. As a promising solution to address these challenges, Transfer Learning (TL) enables DL networks trained on a source domain and task to be applied to a separate target domain and task. This paper presents a domain adversarial TL approach, based upon the concepts of generative adversarial networks. In this method, the optimizer seeks to minimize the loss (i.e., regression or classification accuracy) across the labeled training examples from the source domain while maximizing the loss of the domain classifier across the source and target data sets (i.e., maximizing the similarity of source and target features). The developed domain adversarial TL method has been implemented on a 1-D CNN backbone network and evaluated for prediction of tool wear propagation, using NASA's milling dataset. Performance has been compared to other TL techniques, and the results indicate that domain adversarial TL can successfully allow DL models trained on certain scenarios to be applied to new target tasks.

Tropical cyclones (TCs) are among the most severe and destructive natural events, and they have a major detrimental impact on both the economy and society. This study used Geo-KOMPSAT-2A (GK2A) satellite data to estimate TC intensity in the western North Pacific based on a convolutional neural network (CNN) model. Given that the GK2A data cover only the period since 2019, we applied transfer learning to the model using information learned from previous Communication, Ocean, and Meteorological Satellite (COMS) data, which cover a considerably longer period (2011–2019). Transfer learning is a powerful technique that can improve the performance of a model even if the target task is based on a small amount of data. Experiments with various transfer learning methods using the GK2A and COMS data showed that the frozen–fine-tuning method had the best performance due to the high similarity between the two datasets. The test results for 2021 showed that employing transfer learning led to a 20% reduction in the root mean square error (RMSE) compared to models using only GK2A data. For the operational model, which additionally used TC images and intensities from six hours earlier, transfer learning reduced the RMSE by 5.5%. Because continuous long-term data are not always available for TC intensity estimation based on geostationary satellite images, these results imply that transfer learning may constitute a new advance in this area. Acknowledgement. This research was supported by Korea Institute of Marine Science & Technology Promotion (KIMST) funded by the Korea Coast Guard (RS-2023-00238652, Integrated Satellite-based Applications Development for Korea Coast Guard).  

Recently, there has been a growing interest in the development of intelligent labelfree structural damage identification methods that utilize physics-informed neural networks (PINNs). However, penalizing the governing equation of training data is computationally time-consuming since the existence of high-order partial derivatives. To address this issue, a damage identification method for isotropic and homogeneous thin plates is proposed in this paper that utilizes transfer learning physics-informed neural networks (TL-PINNs). TL-PINNs are efficient PINNs that solve inverse problems by leveraging transfer learning. Transfer learning is a machine learning technique that leverages knowledge from a source task to enhance performance on a related but different target task. It involves reusing a source model trained on a source task and then fine-tuning it to a target model with a target task. In the proposed method, the source model is trained to minimize the mismatch between training data and its predictions. Then, it is finetuned as the target model by minimizing both the mismatch between training data and its predictions as well as residuals that penalize the governing equation of isotropic and homogeneous thin plates. It is resulting in fewer iterations being required in training to penalize the governing equation than those in PINNs, which is time-consuming for highorder partial derivatives using automatic differentiation. Hence, TL-PINNs have a substantial reduction in computational time compared to PINNs for damage identification. A trained TL-PINN from a measured flexural guided wavefield is referred to as a pseudopristine model since it can generate a wavefield that approximates that governed by an isotropic and homogeneous thin plate. This unique functionality arises from penalizing the governing equation in the target model and the fact that the governing equation does not consider the existence of the damage. Any local anomalies in the measured wavefield can be isolated by comparing them with the wavefield generated by the pseudo-pristine model and then intensified using the Teager energy operator. An accumulative damage index is formulated, and the damage can be identified within neighborhoods with high index values. The effectiveness of the proposed method is demonstrated through a numerical investigation. A parameter study is also conducted to investigate the robustness of TL-PINNs with different hyper-parameters.

Prediction of protein-protein interaction (PPI) is one of the most challenging problems in biology. Although great progress has been devoted to the development of methodology for predicting PPIs and PIN using machine learning methods, the problem is still far from being solved since the application of most existing methods is limited. In this study, we propose a method for PPI prediction based on amino acids differences between pairs of protein sequences. 10-fold cross-validation tests based on human PPI datasets with balanced positive-to-negative ratios indicate that it performs comparably well. Therefore, our finding suggests that amino acids differences of interacting protein pairs are relevant to the prediction of PPIs and hence provide important information on sequence-based encoding schemes.

Distance metric learning (DML) is a critical factor for image analysis and pattern recognition. To learn a robust distance metric for a target task, we need abundant side information (i.e., the similarity/dissimilarity pairwise constraints over the labeled data), which is usually unavailable in practice due to the high labeling cost. This paper considers the transfer learning setting by exploiting the large quantity of side information from certain related, but different source tasks to help with target metric learning (with only a little side information). The state-of-the-art metric learning algorithms usually fail in this setting because the data distributions of the source task and target task are often quite different. We address this problem by assuming that the target distance metric lies in the space spanned by the eigenvectors of the source metrics (or other randomly generated bases). The target metric is represented as a combination of the base metrics, which are computed using the decomposed components of the source metrics (or simply a set of random bases); we call the proposed method, decomposition-based transfer DML (DTDML). In particular, DTDML learns a sparse combination of the base metrics to construct the target metric by forcing the target metric to be close to an integration of the source metrics. The main advantage of the proposed method compared with existing transfer metric learning approaches is that we directly learn the base metric coefficients instead of the target metric. To this end, far fewer variables need to be learned. We therefore obtain more reliable solutions given the limited side information and the optimization tends to be faster. Experiments on the popular handwritten image (digit, letter) classification and challenge natural image annotation tasks demonstrate the effectiveness of the proposed method.

A key objective of transfer learning is to improve and speed-up learning on a target task after training on a different, but related, source task. This study presents a neuro-evolution method that transfers evolved policies within multi-agent tasks of varying degrees of complexity. The method incorporates behavioral diversity (novelty) search as a means to boost the task performance of transferred policies (multi-agent behaviors). Results indicate that transferred evolved multi-agent behaviors are significantly improved in more complex tasks when adapted using behavioral diversity. Comparatively, behaviors that do not use behavioral diversity to further adapt transferred behaviors, perform relatively poorly in terms of adaptation times and quality of solutions in target tasks. Also, in support of previous work, both policy transfer methods (with and without behavioral diversity adaptation), out-perform behaviors evolved in target tasks without transfer learning.

Ice-accretion on blades of a wind turbine will cause power degradation and threaten the operating safety of the unit. The use of a machine learning method for ice detection is a promising solution. However, it is costly and infeasible to establish a well-trained model for each individual unit. This paper proposes an inductive transfer learning method to address this problem. The inductive transfer learning aims to improve the detection performance by transferring knowledge from a well-established model. As there is a distribution divergence between the source and target domain, most instance-transfer-based learning methods realize the knowledge transfer by re-weighting the instance in the source domain. In this paper, we propose a novel adaptive inductive transfer learning (adaptive ITL) method for wind turbine ice detection. The knowledge transfer is achieved by offering a relatively stable prediction for the target task through the established model trained in source task. Two auxiliary classifiers are then employed to correct the prediction error of the previous prediction. The model in the source domain and two auxiliary classifiers are combined into a whole model to make a further prediction for the target task. The experimental results on ice detection in wind turbine demonstrate that the proposed adaptive ITL method can significantly improve the performance of the basic instance-transfer-based model and is superior to the state-of-the-art inductive transfer learning methods.