Domain adaptation has become a prominent problem setting in machine learning and related fields. This review asks the question: How can a classifier learn from a source domain and generalize to a target domain? We present a categorization of approaches, divided into, what we refer to as, sample-based , feature-based, and inference-based methods. Sample-based methods focus on weighting individual observations during training based on their importance to the target domain. Feature-based methods revolve around on mapping, projecting, and representing features such that a source classifier performs well on the target domain and inference-based methods incorporate adaptation into the parameter estimation procedure, for instance through constraints on the optimization procedure. Additionally, we review a number of conditions that allow for formulating bounds on the cross-domain generalization error. Our categorization highlights recurring ideas and raises questions important to further research.

A Review of Domain Adaptation without Target Labels

The classic supervised machine learning paradigm is based on learning in isolation, a single predictive model for a task using a single dataset. This approach requires a large number of training examples and performs best for well-defined and narrow tasks. Transfer learning refers to a set of methods that extend this approach by leveraging data from additional domains or tasks to train a model with better generalization properties. Over the last two years, the field of Natural Language Processing (NLP) has witnessed the emergence of several transfer learning methods and architectures which significantly improved upon the state-of-the-art on a wide range of NLP tasks. These improvements together with the wide availability and ease of integration of these methods are reminiscent of the factors that led to the success of pretrained word embeddings and ImageNet pretraining in computer vision, and indicate that these methods will likely become a common tool in the NLP landscape as well as an important research direction. We will present an overview of modern transfer learning methods in NLP, how models are pre-trained, what information the representations they learn capture, and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks.

Transfer Learning in Natural Language Processing.

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample, then there will be differences between how the training data is distributed and how the test data is distributed. Standard classifiers cannot cope with changes in data distributions between training and test phases, and will not perform well. Domain adaptation and transfer learning are sub-fields within machine learning that are concerned with accounting for these types of changes. Here, we present an introduction to these fields, guided by the question: when and how can a classifier generalize from a source to a target domain? We will start with a brief introduction into risk minimization, and how transfer learning and domain adaptation expand upon this framework. Following that, we discuss three special cases of data set shift, namely prior, covariate and concept shift. For more complex domain shifts, there are a wide variety of approaches. These are categorized into: importance-weighting, subspace mapping, domain-invariant spaces, feature augmentation, minimax estimators and robust algorithms. A number of points will arise, which we will discuss in the last section. We conclude with the remark that many open questions will have to be addressed before transfer learners and domain-adaptive classifiers become practical.

An introduction to domain adaptation and transfer learning.

Transfer learning, which leverages knowledge from source domains to enhance learning ability in a target domain, has been proven effective in various applications One major limitation of transfer learning is that the source and target domains should be directly related If there is little overlap between the two domains, performing knowledge transfer between these domains will not be effective Inspired by human transitive inference and learning ability, whereby two seemingly unrelated concepts can be connected by a string of intermediate bridges using auxiliary concepts, in this paper we study a novel learning problem: Transitive Transfer Learning (abbreviated to TTL) TTL is aimed at breaking the large domain distances and transfer knowledge even when the source and target domains share few factors directly For example, when the source and target domains are documents and images respectively, TTL could use some annotated images as the intermediate domain to bridge them To solve the TTL problem, we propose a learning framework to mimic the human learning process The framework is composed of an intermediate domain selection component and a knowledge transfer component Extensive empirical evidence shows that the framework yields state-of-the-art classification accuracies on several classification data sets

http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/97/2015_Transitive_Transfer_Learning.pdf

Transitive Transfer Learning

Machine learning and data mining have found many applications in biological domains, where we look to build predictive models based on labeled training data. However, in practice, high quality labeled data is scarce, and to label new data incurs high costs. Transfer and multitask learning offer an attractive alternative, by allowing useful knowledge to be extracted and transferred from data in auxiliary domains helps counter the lack of data problem in the target domain. In this article, we survey recent advances in transfer and multitask learning for bioinformatics applications. In particular, we survey several key bioinformatics application areas, including sequence classification, gene expression data analysis, biological network reconstruction and biomedical applications. Category: Convergence computing

/pdf/a-survey-of-transfer-and-multitask-learning-in-4kf2yp23xc.pdf

A Survey of Transfer and Multitask Learning in Bioinformatics

A new method for multitask learning in a Bayesian network context is presented for multiorganism gene network estimation. When the input datasets are sparse, as is the case in microarray gene expression data, it becomes difficult to separate random correlations from actual edges in the true underlying Bayesian network. Multitask learning takes advantage of the similarity between related tasks, in order to construct a more accurate model of the underlying relationships represented by the Bayesian networks. The proposed method is tested on synthetic data to illustrate its validity. Then it is iteratively applied on real gene expression data to learn the genetic regulatory networks of two organisms with homologous genes (human and yeast).

A new multitask learning method for multiorganism gene network estimation

Raptor codes are a class of concatenated codes composed of a fixed-rate precode and a Luby-transform (LT) code that can be used as rateless error-correcting codes over communication channels. These codes have the atypical features of dynamic code-rate, highly irregular Tanner graph check-degree distribution, random LT-code structure, and LT-precode concatenation, which render a hardware-efficient decoder implementation achieving good error-correcting performance a challenging task. In this paper, the design of hardware-efficient Raptor decoders with good performance is addressed through joint optimizations targeting 1) the code construction, 2) decoding schedule, and 3) decoder architecture. First, random encoding is decoupled by developing a two-stage LT-code construction scheme that embeds structural features in the LT-graph that are amenable to efficient implementation while guaranteeing good performance. An LT-aware LDPC precode construction methodology that ensures architectural-compatibility with the structured LT code is also proposed. Second, a decoding schedule is optimized to reduce memory cost and account for processing workload-variability caused by the varying code rate. Third, to address the problems of check-degree irregularity and hardware underutilization, a novel reconfigurable check unit that attains a constant throughput while processing a varying number of LT and LDPC nodes is presented. These design steps collectively are employed to generate serial and partially-parallel decoder architectures. A Raptor code instance constructed using the proposed method having LT data-block length of 1210 is shown to outperform or closely match the performance of conventional LDPC codes over the code-rate range [0.4,2/3]. The corresponding hardware serial decoder is synthesized using 65-nm CMOS technology and achieves a throughput of 22 Mb/s at rate 0.4 for a BER of 10-6, dissipates an average power of 222 mW at 1.2 V, and occupies an area of 1.77mm2.

Construction and Hardware-Efficient Decoding of Raptor Codes

We address the challenge of implementing reliable computation of Boolean functions in future nanocircuit fabrics. Such fabrics are projected to have very high defect rates. We overcome this limitation by using a combination of cheap but unreliable nanodevices and reliable but expensive CMOS devices. The contribution of this work is twofold - (1) A heterogeneous architecture suitable for low level defect tolerance (2) A novel coding strategy that for the first time exploited the structure of Boolean function for better coder. In our approach, defect tolerance is achieved through a novel coding of Boolean functions; specifically, we exploit the don't cares of Boolean functions encountered in multi-level Boolean logic networks for constructing better codes. The optimal coding problem is NP-hard. We solved it with a SAT based heuristic. We show that compared to direct application of existing coding techniques, the coding overhead in terms of extra bits can be reduced, on average by 23%, and savings can go up to 34%. We demonstrate that by incorporating efficient coding techniques more than a 20% average yield improvement is possible in case of 10% defect rates. We incur a negligible delay penalty of less than 1% for decoder and the area is 13X smaller compared 22 nm CMOS technology and 32% smaller than TMR (triple modular redundancy) coding scheme.

A heterogeneous CMOS-CNT architecture utilizing novel coding of boolean functions

A novel inter-frame coding approach to the problem of varying channel-state conditions in broadcast wireless communication is developed in this paper; this problem causes the appropriate code-rate to vary across different transmitted frames and different receivers as well. The main aspect of the proposed approach is that it incorporates an iterative rate-matching process into the decoding of the received set of frames, such that: throughout inter-frame decoding, the code-rate of each frame is progressively lowered to or below the appropriate value, and prior to applying or re-applying conventional physical-layer channel decoding on it. This iterative rate-matching process is asymptotically analyzed in this paper. It is shown to be optimal, in the sense defined in the paper. Consequently, the data-rates achievable by the proposed scheme are derived. Overall, it is concluded that, compared to the existing solutions, inter-frame coding presents a better complexity versus data-rate tradeoff. In terms of complexity, the overhead of inter-frame decoding includes operations that are similar in type and scheduling to those employed in the relatively-simple iterative erasure decoding. In terms of data-rates, compared to the state-of-the-art two-stage scheme involving both error-correcting and erasure coding, inter-frame coding increases the data-rate by a factor that reaches up to $1.55\times$ .

Inter-Frame Coding For Broadcast Communication

A novel inter-frame coding approach to the problem of varying channel-state conditions in broadcast wireless communication is developed in this paper; this problem causes the appropriate code-rate to vary across different transmitted frames and different receivers as well. The main aspect of the proposed approach is that it incorporates an iterative rate-matching process into the decoding of the received set of frames, such that: throughout inter-frame decoding, the code-rate of each frame is progressively lowered to or below the appropriate value, prior to applying or re-applying conventional physical-layer channel decoding on it. This iterative rate-matching process is asymptotically analyzed in this paper. It is shown to be optimal, in the sense defined in the paper. Consequently, the data-rates achievable by the proposed scheme are derived. Overall, it is concluded that, compared to the existing solutions, inter-frame coding presents a better complexity versus data-rate tradeoff. In terms of complexity, the overhead of inter-frame decoding includes operations that are similar in type and scheduling to those employed in the relatively- simple iterative erasure decoding. In terms of data-rates, compared to the state-of-the-art two-stage scheme involving both error-correcting and erasure coding, inter-frame coding increases the data-rate by a factor that reaches up to 1.55x.

Hady Zeineddine

Papers

A new multitask learning method for multiorganism gene network estimation

Construction and Hardware-Efficient Decoding of Raptor Codes

A heterogeneous CMOS-CNT architecture utilizing novel coding of boolean functions

Inter-Frame Coding For Broadcast Communication

Inter-Frame Coding For Broadcast Communication