Research papers and code for "transfer learning":
Transfer learning borrows knowledge from a source domain to facilitate learning in a target domain. Two primary issues to be addressed in transfer learning are what and how to transfer. For a pair of domains, adopting different transfer learning algorithms results in different knowledge transferred between them. To discover the optimal transfer learning algorithm that maximally improves the learning performance in the target domain, researchers have to exhaustively explore all existing transfer learning algorithms, which is computationally intractable. As a trade-off, a sub-optimal algorithm is selected, which requires considerable expertise in an ad-hoc way. Meanwhile, it is widely accepted in educational psychology that human beings improve transfer learning skills of deciding what to transfer through meta-cognitive reflection on inductive transfer learning practices. Motivated by this, we propose a novel transfer learning framework known as Learning to Transfer (L2T) to automatically determine what and how to transfer are the best by leveraging previous transfer learning experiences. We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function. Extensive experiments demonstrate the L2T's superiority over several state-of-the-art transfer learning algorithms and its effectiveness on discovering more transferable knowledge.

* 12 pages, 8 figures, conference
Click to Read Paper and Get Code
We consider a transfer-learning problem by using the parameter transfer approach, where a suitable parameter of feature mapping is learned through one task and applied to another objective task. Then, we introduce the notion of the local stability and parameter transfer learnability of parametric feature mapping,and thereby derive a learning bound for parameter transfer algorithms. As an application of parameter transfer learning, we discuss the performance of sparse coding in self-taught learning. Although self-taught learning algorithms with plentiful unlabeled data often show excellent empirical performance, their theoretical analysis has not been studied. In this paper, we also provide the first theoretical learning bound for self-taught learning.

* This paper was accepted at NIPS 2016 as a poster presentation
Click to Read Paper and Get Code
As the application of deep learning has expanded to real-world problems with insufficient volume of training data, transfer learning recently has gained much attention as means of improving the performance in such small-data regime. However, when existing methods are applied between heterogeneous architectures and tasks, it becomes more important to manage their detailed configurations and often requires exhaustive tuning on them for the desired performance. To address the issue, we propose a novel transfer learning approach based on meta-learning that can automatically learn what knowledge to transfer from the source network to where in the target network. Given source and target networks, we propose an efficient training scheme to learn meta-networks that decide (a) which pairs of layers between the source and target networks should be matched for knowledge transfer and (b) which features and how much knowledge from each feature should be transferred. We validate our meta-transfer approach against recent transfer learning methods on various datasets and network architectures, on which our automated scheme significantly outperforms the prior baselines that find "what and where to transfer" in a hand-crafted manner.

* Accepted to ICML 2019
Click to Read Paper and Get Code
Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network (RNN), represents the sequential information transfer. RNN uses a chain of repeating cells to model the sequence data. However, previous studies of neural network based transfer learning simply represents the whole sentence by a single vector, which is unfeasible for seq2seq and sequence labeling. Meanwhile, such layer-wise transfer learning mechanisms lose the fine-grained cell-level information from the source domain. In this paper, we proposed the aligned recurrent transfer, ART, to achieve cell-level information transfer. ART is under the pre-training framework. Each cell attentively accepts transferred information from a set of positions in the source domain. Therefore, ART learns the cross-domain word collocations in a more flexible way. We conducted extensive experiments on both sequence labeling tasks (POS tagging, NER) and sentence classification (sentiment analysis). ART outperforms the state-of-the-arts over all experiments.

* Published at ICLR 2019
Click to Read Paper and Get Code
Deep text matching approaches have been widely studied for many applications including question answering and information retrieval systems. To deal with a domain that has insufficient labeled data, these approaches can be used in a Transfer Learning (TL) setting to leverage labeled data from a resource-rich source domain. To achieve better performance, source domain data selection is essential in this process to prevent the "negative transfer" problem. However, the emerging deep transfer models do not fit well with most existing data selection methods, because the data selection policy and the transfer learning model are not jointly trained, leading to sub-optimal training efficiency. In this paper, we propose a novel reinforced data selector to select high-quality source domain data to help the TL model. Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector. We build the reinforced data selector based on the actor-critic framework and integrate it to a DNN based transfer learning model, resulting in a Reinforced Transfer Learning (RTL) method. We perform a thorough experimental evaluation on two major tasks for text matching, namely, paraphrase identification and natural language inference. Experimental results show the proposed RTL can significantly improve the performance of the TL model. We further investigate different settings of states, rewards, and policy optimization methods to examine the robustness of our method. Last, we conduct a case study on the selected data and find our method is able to select source domain data whose Wasserstein distance is close to the target domain data. This is reasonable and intuitive as such source domain data can provide more transferability power to the model.

* Accepted to WSDM 2019
Click to Read Paper and Get Code
The introduction of deep learning and transfer learning techniques in fields such as computer vision allowed a leap forward in the accuracy of image classification tasks. Currently there is only limited use of such techniques in neuroscience. The challenge of using deep learning methods to successfully train models in neuroscience, lies in the complexity of the information that is processed, the availability of data and the cost of producing sufficient high quality annotations. Inspired by its application in computer vision, we introduce transfer learning on electrophysiological data to enable training a model with limited amounts of data. Our method was tested on the dataset of the BCI competition IV 2a and compared to the top results that were obtained using traditional machine learning techniques. Using our DL model we outperform the top result of the competition by 33%. We also explore transferability of knowledge between trained models over different experiments, called inter-experimental transfer learning. This reduces the amount of required data even further and is especially useful when few subjects are available. This method is able to outperform the standard deep learning methods used in the BCI competition IV 2b approaches by 18%. In this project we propose a method that can produce reliable electroencephalography (EEG) signal classification, based on modest amounts of training data through the use of transfer learning.

* 14 pages, 6 figures
Click to Read Paper and Get Code
Background: Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, excretion prediction models still have limited accuracy. Aim: This study aims to construct an integrated transfer learning and multitask learning approach for developing quantitative structure-activity relationship models to predict four human pharmacokinetic parameters. Methods: A pharmacokinetic dataset included 1104 U.S. FDA approved small molecule drugs. The dataset included four human pharmacokinetic parameter subsets (oral bioavailability, plasma protein binding rate, apparent volume of distribution at steady-state and elimination half-life). The pre-trained model was trained on over 30 million bioactivity data. An integrated transfer learning and multitask learning approach was established to enhance the model generalization. Results: The pharmacokinetic dataset was split into three parts (60:20:20) for training, validation and test by the improved Maximum Dissimilarity algorithm with the representative initial set selection algorithm and the weighted distance function. The multitask learning techniques enhanced the model predictive ability. The integrated transfer learning and multitask learning model demonstrated the best accuracies, because deep neural networks have the general feature extraction ability, transfer learning and multitask learning improved the model generalization. Conclusions: The integrated transfer learning and multitask learning approach with the improved dataset splitting algorithm was firstly introduced to predict the pharmacokinetic parameters. This method can be further employed in drug discovery and development.

Click to Read Paper and Get Code
Real-time strategy games have been an important field of game artificial intelligence in recent years. This paper presents a reinforcement learning and curriculum transfer learning method to control multiple units in StarCraft micromanagement. We define an efficient state representation, which breaks down the complexity caused by the large state space in the game environment. Then a parameter sharing multi-agent gradientdescent Sarsa({\lambda}) (PS-MAGDS) algorithm is proposed to train the units. The learning policy is shared among our units to encourage cooperative behaviors. We use a neural network as a function approximator to estimate the action-value function, and propose a reward function to help units balance their move and attack. In addition, a transfer learning method is used to extend our model to more difficult scenarios, which accelerates the training process and improves the learning performance. In small scale scenarios, our units successfully learn to combat and defeat the built-in AI with 100% win rates. In large scale scenarios, curriculum transfer learning method is used to progressively train a group of units, and shows superior performance over some baseline methods in target scenarios. With reinforcement learning and curriculum transfer learning, our units are able to learn appropriate strategies in StarCraft micromanagement scenarios.

* 12 pages, 14 figures, accepted to IEEE Transactions on Emerging Topics in Computational Intelligence
Click to Read Paper and Get Code
Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from the source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as a constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.

* International Conference on Computer Vision and Pattern Recognition, 2016
Click to Read Paper and Get Code
People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to train invariant feature spaces that can then be used to transfer other skills from one agent to another. The process of learning these invariant feature spaces can be viewed as a kind of "analogy making", or implicit learning of partial correspondences between two distinct domains. We evaluate our transfer learning algorithm in two simulated robotic manipulation skills, and illustrate that we can transfer knowledge between simulated robotic arms with different numbers of links, as well as simulated arms with different actuation mechanisms, where one robot is torque-driven while the other is tendon-driven.

* Published as a conference paper at ICLR 2017
Click to Read Paper and Get Code
Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converges slowly comparing to supervised learning, different kinds of transfer RL algorithms are designed. However, most of them are heuristic with no theoretical guarantee of the convergence rate. Therefore, it is important for us to clearly understand when and how will transfer learning help RL method and provide the theoretical guarantee for the improvement of the sample complexity. In this paper, we propose to transfer the Q-function learned in the source task to the target of the Q-learning in the new task when certain safe conditions are satisfied. We call this new transfer Q-learning method target transfer Q-Learning. The safe conditions are necessary to avoid the harm to the new tasks and thus ensure the convergence of the algorithm. We study the convergence rate of the target transfer Q-learning. We prove that if the two tasks are similar with respect to the MDPs, the optimal Q-functions in the source and new RL tasks are similar which means the error of the transferred target Q-function in new MDP is small. Also, the convergence rate analysis shows that the target transfer Q-Learning will converge faster than Q-learning if the error of the transferred target Q-function is smaller than the current Q-function in the new task. Based on our theoretical results, we design the safe condition as the Bellman error of the transferred target Q-function is less than the current Q-function. Our experiments are consistent with our theoretical founding and verified the effectiveness of our proposed target transfer Q-learning method.

Click to Read Paper and Get Code
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, meta-learning typically uses shallow neural networks (SNNs), thus limiting its effectiveness. In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. Specifically, "meta" refers to training multiple tasks, and "transfer" is achieved by learning scaling and shifting functions of DNN weights for each task. In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum for MTL. We conduct experiments using (5-class, 1-shot) and (5-class, 5-shot) recognition tasks on two challenging few-shot learning benchmarks: miniImageNet and Fewshot-CIFAR100. Extensive comparisons to related works validate that our meta-transfer learning approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy.

* Code and supplementary materials will be made public soon. *This work was done during Yaoyao Liu's internship at NUS
Click to Read Paper and Get Code
In complex transfer learning scenarios new tasks might not be tightly linked to previous tasks. Approaches that transfer information contained only in the final parameters of a source model will therefore struggle. Instead, transfer learning at a higher level of abstraction is needed. We propose Leap, a framework that achieves this by transferring knowledge across learning processes. We associate each task with a manifold on which the training process travels from initialization to final parameters and construct a meta learning objective that minimizes the expected length of this path. Our framework leverages only information obtained during training and can be computed on the fly at negligible cost. We demonstrate that our framework outperforms competing methods, both in meta learning and transfer learning, on a set of computer vision tasks. Finally, we demonstrate that Leap can transfer knowledge across learning processes in demanding Reinforcement Learning environments (Atari) that involve millions of gradient steps.

* 22 pages, 8 figures, 6 tables
Click to Read Paper and Get Code
Transfer learning has been proven effective when within-target labeled data is scarce. A lot of works have developed successful algorithms and empirically observed positive transfer effect that improves target generalization error using source knowledge. However, theoretical analysis of transfer learning is more challenging due to the nature of the problem and thus is less studied. In this report, we do a survey of theoretical works in transfer learning and summarize key theoretical guarantees that prove the effectiveness of transfer learning. The theoretical bounds are derived using model complexity and learning algorithm stability. As we should see, these works exhibit a trade-off between tight bounds and restrictive assumptions. Moreover, we also prove a new generalization bound for the multi-source transfer learning problem using the VC-theory, which is more informative than the one proved in previous work.

Click to Read Paper and Get Code
This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer. Furthermore, this paper re-characterizes existing agents-teaching-agents methods as online transfer and analyze one such teaching method in three ways. First, the convergence of Q-learning and Sarsa with tabular representation with a finite budget is proven. Second, the convergence of Q-learning and Sarsa with linear function approximation is established. Third, the we show the asymptotic performance cannot be hurt through teaching. Additionally, all theoretical results are empirically validated.

* 18 pages, 2 figures
Click to Read Paper and Get Code
In recent years, transfer learning gained particular interest in the field of vision and natural language processing. In the research field of vision, e.g., deep neural networks and transfer learning techniques achieve almost perfect classification scores within minutes. Nonetheless, these techniques are not yet widely applied in other domains. Therefore, this article identifies critical challenges and shows potential solutions for power forecasts in the field of renewable energies. It proposes a framework utilizing transfer learning techniques in wind power forecasts with limited or no historical data. On the one hand, this allows evaluating the applicability of transfer learning in the field of renewable energy. On the other hand, by developing automatic procedures, we assure that the proposed methods provide a framework that applies to domains in organic computing as well.

Click to Read Paper and Get Code
Transfer learning leverages the knowledge in one domain, the source domain, to improve learning efficiency in another domain, the target domain. Existing transfer learning research is relatively well-progressed, but only in situations where the feature spaces of the domains are homogeneous and the target domain contains at least a few labeled instances. However, transfer learning has not been well-studied in heterogeneous settings with an unlabeled target domain. To contribute to the research in this emerging field, this paper presents: (1) an unsupervised knowledge transfer theorem that prevents negative transfer; and (2) a principal angle-based metric to measure the distance between two pairs of domains. The metric shows the extent to which homogeneous representations have preserved the information in original source and target domains. The unsupervised knowledge transfer theorem sets out the transfer conditions necessary to prevent negative transfer. Linear monotonic maps meet the transfer conditions of the theorem and, hence, are used to construct homogeneous representations of the heterogeneous domains, which in principle prevents negative transfer. The metric and the theorem have been implemented in an innovative transfer model, called a Grassmann-LMM-geodesic flow kernel (GLG), that is specifically designed for knowledge transfer across heterogeneous domains. The GLG model learns homogeneous representations of heterogeneous domains by minimizing the proposed metric. Knowledge is transferred through these learned representations via a geodesic flow kernel. Notably, the theorem presented in this paper provides the sufficient transfer conditions needed to guarantee that knowledge is transferred from a source domain to an unlabeled target domain with correctness.

Click to Read Paper and Get Code
Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the pre-trained models to the new tasks by fine-tuning. Classic model fine-tuning utilizes the fact that well trained neural networks appear to learn cross domain features. These features are treated equally during transfer learning. In this paper, we explore the impact of feature selection in model fine-tuning by introducing a transfer module, which assigns weights to features extracted from pre-trained models. The proposed transfer module proves the importance of feature selection for transferring models from source to target domains. It is shown to significantly improve upon fine-tuning results with only marginal extra computational cost. We also incorporate an auxiliary classifier as an extra regularizer to avoid over-fitting. Finally, we build a Gated Transfer Network (GTN) based on our transfer module and achieve state-of-the-art results on six different tasks.

* Accepted at ACCV 2018. Camera ready
Click to Read Paper and Get Code
As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation, which limits its development. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to solve the problem of insufficient training data. This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications. We defined deep transfer learning, category and review the recent research works based on the techniques used in deep transfer learning.

* The 27th International Conference on Artificial Neural Networks (ICANN 2018)
Click to Read Paper and Get Code
Many tasks in natural language understanding require learning relationships between two sequences for various tasks such as natural language inference, paraphrasing and entailment. These aforementioned tasks are similar in nature, yet they are often modeled individually. Knowledge transfer can be effective for closely related tasks. However, transferring all knowledge, some of which irrelevant for a target task, can lead to sub-optimal results due to \textit{negative} transfer. Hence, this paper focuses on the transferability of both instances and parameters across natural language understanding tasks by proposing an ensemble-based transfer learning method. \newline The primary contribution of this paper is the combination of both \textit{Dropout} and \textit{Bagging} for improved transferability in neural networks, referred to as \textit{Dropping} herein. We present a straightforward yet novel approach for incorporating source \textit{Dropping} Networks to a target task for few-shot learning that mitigates \textit{negative} transfer. This is achieved by using a decaying parameter chosen according to the slope changes of a smoothed spline error curve at sub-intervals during training. We compare the proposed approach against hard parameter sharing and soft parameter sharing transfer methods in the few-shot learning case. We also compare against models that are fully trained on the target task in the standard supervised learning setup. The aforementioned adjustment leads to improved transfer learning performance and comparable results to the current state of the art only using a fraction of the data from the target task.

* 9 pages, 3 figures Updated because the original table of results was in the wrong order
Click to Read Paper and Get Code