Multi-agent Behavior-Based Policy Transfer

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.

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.

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 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.

Transfer learning has proven to be a wildly successful approach for speeding up reinforcement learning. Techniques often use low-level information obtained in the source task to achieve successful transfer in the target task. Yet, a most general transfer approach can only assume access to the output of the learning algorithm in the source task, i.e. the learned policy, enabling transfer irrespective of the learning algorithm used in the source task. We advance the state-of-the-art by using a reward shaping approach to policy transfer. One of the advantages in following such an approach, is that it firmly grounds policy transfer in an actively developing body of theoretical research on reward shaping. Experiments in Mountain Car, Cart Pole and Mario demonstrate the practical usefulness of the approach.

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.

Neural transfer learning for assigning diagnosis codes to EMRs

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.

The success of transfer to improve learning on a target task is highly dependent on the selected source data. Instance-based transfer methods reuse data from the source tasks to augment the training data for the target task. If poorly chosen, this source data may inhibit learning, resulting in negative transfer. The current best performing algorithm for instance-based transfer, TrAdaBoost, performs poorly when given irrelevant source data. We present a novel set-based boosting technique for instance-based transfer. The proposed algorithm, TransferBoost, boosts both individual instances and collective sets of instances from each source task. In effect, TransferBoost boosts each source task, assigning higher weight to those source tasks which show positive transferability to the target task, and then adjusts the weights of the instances within each source task via AdaBoost. The results demonstrate that TransferBoost significantly improves transfer performance over existing instance-based algorithms when given a mix of relevant and irrelevant source data.

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.