A Unified Meta-Learning Framework for Dynamic Transfer Learning

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?

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.

We consider the problem of building a model to predict protein-protein interactions (PPIs) between the bacterial species Salmonella Typhimurium and the plant host Arabidopsis thaliana which is a host-pathogen pair for which no known PPIs are available. To achieve this, we present approaches, which use homology and statistical learning methods called “transfer learning.” In the transfer learning setting, the task of predicting PPIs between Arabidopsis and its pathogen S. Typhimurium is called the “target task.” The presented approaches utilize labeled data i.e., known PPIs of other host-pathogen pairs (we call these PPIs the “source tasks”). The homology based approaches use heuristics based on biological intuition to predict PPIs. The transfer learning methods use the similarity of the PPIs from the source tasks to the target task to build a model. For a quantitative evaluation we consider Salmonella-mouse PPI prediction and some other host-pathogen tasks where known PPIs exist. We use metrics such as precision and recall and our results show that our methods perform well on the target task in various transfer settings. We present a brief qualitative analysis of the Arabidopsis-Salmonella predicted interactions. We filter the predictions from all approaches using Gene Ontology term enrichment and only those interactions involving Salmonella effectors. Thereby we observe that Arabidopsis proteins involved e.g., in transcriptional regulation, hormone mediated signaling and defense response may be affected by Salmonella.

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.

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.

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.

Neural transfer learning for assigning diagnosis codes to EMRs

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.

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.

We propose using a statistical-relational model, the Markov Logic Network, for knowledge transfer in reinforcement learning. Our goal is to extract relational knowledge from a source task and use it to speed up learning in a related target task. We show that Markov Logic Networks are effective models for capturing both source-task Q-functions and source-task policies. We apply them via demonstration, which involves using them for decision making in an initial stage of the target task before continuing to learn. Through experiments in the RoboCup simulated-soccer domain, we show that transfer via Markov Logic Networks can significantly improve early performance in complex tasks, and that transferring policies is more effective than transferring Q-functions.

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained on the source task using data from the target task. In this paper, we propose an adaptive fine-tuning approach, called SpotTune, which finds the optimal fine-tuning strategy per instance for the target data. In SpotTune, given an image from the target task, a policy network is used to make routing decisions on whether to pass the image through the fine-tuned layers or the pre-trained layers. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach. Our method outperforms the traditional fine-tuning approach on 12 out of 14 standard datasets.We also compare SpotTune with other state-of-the-art fine-tuning strategies, showing superior performance. On the Visual Decathlon datasets, our method achieves the highest score across the board without bells and whistles.

Evolutionary sequential transfer optimization is a paradigm that leverages search experience from solved source optimization tasks to accelerate the evolutionary search of a target task. Even though many algorithms have been developed, they mainly focus on objective-homogeneous problems, where the source and target tasks possess a similar number of objectives. In this work, we explore objective-heterogeneous problems, in which knowledge transfers across single-objective optimization problems (SOPs), multiobjective optimization problems (MOPs), and many-objective optimization problems (MaOPs). Objective-heterogeneous problems challenge the existing methods due to the diverse search and objective spaces between the source and the target task. To address this issue, we present a decision variable analysis-based transfer method that can conduct knowledge transfer across problems with the different numbers of objectives. We first separate decision variables of MOPs and MaOPs into convergence-related variables (CVs) and diversity-related variables (DVs), according to their roles while treating variables of SOPs as CVs. Then, we propose a convergence transfer module to transfer knowledge of CVs to speed up the convergence. It aligns both solutions and fitness ranks for preserving fitness rank consistency between the source and target tasks, whereby accelerating search speed. Besides, a diversity transfer module is presented to refine the distribution of DVs to maintain the population diversity. The experimental results on objective-heterogeneous test problems and a real-world case study have demonstrated the effectiveness of the proposed algorithm.

A frequent problem when dealing with audio classification tasks is the scarcity of suitable training data. This work investigates ways of mitigating this problem by applying transfer learning techniques to neural network architectures for several classification tasks from the field of Music Information Retrieval (MIR). First, three state-of-the-art architectures are trained and evaluated with several datasets for the task of speech/music classification. Second, feature representations or embeddings are extracted from the trained networks to classify new tasks with unseen data. The effect of pre-training with respect to the similarity of the source and target tasks are investigated in the context of transfer learning, as well as different fine-tuning strategies.

Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries