相关论文
2009 - 2008 IEEE International Conference on Robotics and Biomimetics
Rearrangement of multiple objects by a robot group having a multi-task function

A robot having a multi-task function can carry more than two objects simultaneously; however, a robot without that function can carry only one at any given time. A multi-task function robot has the potential to shorten the transfer path, which reduces the process time; however, a single-function robot does not have that capability. In this paper, a planning algorithm that consists of Simulated Annealing and Scheduling with prioritization rules for a robot group having a multi-task function is proposed. Experiments are conducted in a real environment to validate the proposed algorithms.

2021 - Neural Comput. Appl.
Statistically correlated multi-task learning for autonomous driving

Autonomous driving research is an emerging area in the machine learning domain. Most existing methods perform single-task learning, while multi-task learning (MTL) is more efficient due to the leverage of shared information between different tasks. However, MTL is challenging because different tasks may have different significance and varying ranges. In this work, we propose an end-to-end deep learning architecture for statistically correlated MTL using a single input image. Statistical correlation of the tasks is handled by including shared layers in the architecture. Later network separates into different branches to handle the difference in the behavior of each task. Training a multi-task model with varying ranges may converge the objective function only with larger values. To this end, we explore different normalization schemes and empirically observe that the inverse validation-loss weighted scheme has best performed. In addition to estimating steering angle, braking, and acceleration, we also estimate the number of lanes on the left and the right side of the vehicle. To the best of our knowledge, we are the first to propose an end-to-end deep learning architecture to estimate this type of lane information. The proposed approach is evaluated on four publicly available datasets including Comma.ai, Udacity, Berkeley Deep Drive, and Sully Chen. We also propose a synthetic dataset GTA-V for autonomous driving research. Our experiments demonstrate the superior performance of the proposed approach compared to the current state-of-the-art methods. The GTA-V dataset and the lane annotations on the four existing datasets will be made publicly available via https://cvlab.lums.edu.pk/scmtl/.

2020 - ArXiv
Deeper Task-Specificity Improves Joint Entity and Relation Extraction

Multi-task learning (MTL) is an effective method for learning related tasks, but designing MTL models necessitates deciding which and how many parameters should be task-specific, as opposed to shared between tasks. We investigate this issue for the problem of jointly learning named entity recognition (NER) and relation extraction (RE) and propose a novel neural architecture that allows for deeper task-specificity than does prior work. In particular, we introduce additional task-specific bidirectional RNN layers for both the NER and RE tasks and tune the number of shared and task-specific layers separately for different datasets. We achieve state-of-the-art (SOTA) results for both tasks on the ADE dataset; on the CoNLL04 dataset, we achieve SOTA results on the NER task and competitive results on the RE task while using an order of magnitude fewer trainable parameters than the current SOTA architecture. An ablation study confirms the importance of the additional task-specific layers for achieving these results. Our work suggests that previous solutions to joint NER and RE undervalue task-specificity and demonstrates the importance of correctly balancing the number of shared and task-specific parameters for MTL approaches in general.

2020 - ArXiv
Task Uncertainty Loss Reduce Negative Transfer in Asymmetric Multi-task Feature Learning

Multi-task learning (MTL) is frequently used in settings where a target task has to be learnt based on limited training data, but knowledge can be leveraged from related auxiliary tasks. While MTL can improve task performance overall relative to single-task learning (STL), these improvements can hide negative transfer (NT), where STL may deliver better performance for many individual tasks. Asymmetric multitask feature learning (AMTFL) is an approach that tries to address this by allowing tasks with higher loss values to have smaller influence on feature representations for learning other tasks. Task loss values do not necessarily indicate reliability of models for a specific task. We present examples of NT in two orthogonal datasets (image recognition and pharmacogenomics) and tackle this challenge by using aleatoric homoscedastic uncertainty to capture the relative confidence between tasks, and set weights for task loss. Our results show that this approach reduces NT providing a new approach to enable robust MTL.

2020 - ArXiv
A Multi-task Learning Framework for Opinion Triplet Extraction

The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of aspect-sentiment pairs lacks opinion terms as a reference, while co-extraction of aspect and opinion terms would not lead to meaningful pairs without determining their sentiment dependencies. To address the issue, we present a novel view of ABSA as an opinion triplet extraction task, and propose a multi-task learning framework to jointly extract aspect terms and opinion terms, and simultaneously parses sentiment dependencies between them with a biaffine scorer. At inference phase, the extraction of triplets is facilitated by a triplet decoding method based on the above outputs. We evaluate the proposed framework on four SemEval benchmarks for ASBA. The results demonstrate that our approach significantly outperforms a range of strong baselines and state-of-the-art approaches.

2020 - Computers in biology and medicine
Effect of deep transfer and multi-task learning on sperm abnormality detection

Analyzing the abnormality of morphological characteristics of male human sperm has been studied for a long time mainly because it has many implications on the male infertility problem, which accounts for approximately half of the infertility problems in the world. Yet, detecting such abnormalities by embryologists has several downsides. To clarify, analyzing sperms through visual inspection of an expert embryologist is a highly subjective and biased process. Furthermore, it takes much time for a specialist to make a diagnosis. Hence, in this paper, we proposed two deep learning algorithms that are able to automate this process. The first algorithm uses a network-based deep transfer learning approach, while the second technique, named Deep Multi-task Transfer Learning (DMTL), employs a novel combination of network-based deep transfer learning and multi-task learning to classify sperm's head, vacuole, and acrosome as either normal or abnormal. This DMTL technique is capable of classifying all the aforementioned parts of the sperm in a single prediction. Moreover, this is the first time that the concept of multi-task learning has been introduced to the field of Sperm Morphology Analysis (SMA). To benchmark our algorithms, we employed a freely-available SMA dataset named MHSMA. During our experiments, our algorithms reached the state-of-the-art results on the accuracy, precision, and f0.5, as well as other important metrics, such as the Matthews Correlation Coefficient on one, two, or all three labels. Notably, our algorithms increased the accuracy of the head, acrosome, and vacuole by 6.66%, 3.00%, and 1.33%, and reached the accuracy of 84.00%, 80.66%, and 94.00% on these labels, respectively. Consequently, our algorithms can be used in health institutions, such as fertility clinics, with further recommendations to practically improve the performance of our algorithms.

2004 - Canadian Conference on AI
Sequential Consolidation of Learned Task Knowledge

A fundamental problem of life-long machine learning is how to consolidate the knowledge of a learned task within a long-term memory structure (domain knowledge) without the loss of prior knowledge. Consolidated domain knowledge makes more efficient use of memory and can be used for more efficient and effective transfer of knowledge when learning future tasks. Relevant background material on knowledge based inductive learning and the transfer of task knowledge using multiple task learning (MTL) neural networks is reviewed. A theory of task knowledge consolidation is presented that uses a large MTL network as the long-term memory structure and task rehearsal to overcome the stability-plasticity problem and the loss of prior knowledge. The theory is tested on a synthetic domain of diverse tasks and it is shown that, under the proper conditions, task knowledge can be sequentially consolidated within an MTL network without loss of prior knowledge. In fact, a steady increase in the accuracy of consolidated domain knowledge is observed.

2016 - 2016 American Control Conference (ACC)
An MILP approach for real-time optimal controller synthesis with Metric Temporal Logic specifications

The fundamental idea of this work is to synthesize reactive controllers such that closed-loop execution trajectories of the system satisfies desired specifications that ensure correct system behaviors, while optimizing a desired performance criteria. We define the correctness of a system's behavior according to the system's relation to the environment, for example, the output trajectories of the system terminate in a goal set without entering an unsafe set. Using Metric Temporal Logic (MTL) specifications we can capture complex system behaviors and timing requirements, such as the output trajectories must pass through a number of way-points within a certain time frame before terminating in the goal set. Given a Mixed Logical Dynamical (MLD) system and system specifications in terms of MTL formula or simpler reach-avoid specifications, our goal is to find a closed-loop trajectory that satisfies the specifications, in non-deterministic environments. Using an MILP framework we search over the space of input signals to obtain such valid trajectories of the system, by adding constraints to satisfy the MTL formula only when necessary, to avoid the exponential complexity of solving MILP problems. We also present experimental results for planning a path in real-time for a mobile robot through a dynamically changing environment with a desired task specification.

2015 - NIPS
Efficient Output Kernel Learning for Multiple Tasks

The paradigm of multi-task learning is that one can achieve better generalization by learning tasks jointly and thus exploiting the similarity between the tasks rather than learning them independently of each other. While previously the relationship between tasks had to be user-defined in the form of an output kernel, recent approaches jointly learn the tasks and the output kernel. As the output kernel is a positive semidefinite matrix, the resulting optimization problems are not scalable in the number of tasks as an eigendecomposition is required in each step. Using the theory of positive semidefinite kernels we show in this paper that for a certain class of regularizers on the output kernel, the constraint of being positive semidefinite can be dropped as it is automatically satisfied for the relaxed problem. This leads to an unconstrained dual problem which can be solved efficiently. Experiments on several multi-task and multi-class data sets illustrate the efficacy of our approach in terms of computational efficiency as well as generalization performance.

2002 - Reviews in the Neurosciences
The Interaction of Rhinal Cortex and Hippocampus in Human Declarative Memory Formation

Human declarative memory formation crucially depends on processes within the medial temporal lobe (MTL). These processes can be monitored in real-time by recordings from depth electrodes implanted in the MTL of patients with epilepsy who undergo presurgical evaluation. In our studies, patients performed a word memorization task during depth EEG recording. Afterwards, the difference between event-related potentials (ERPs) corresponding to subsequently remembered versus forgotten words was analyzed. These kind of studies revealed that successful memory encoding is characterized by an early process generated by the rhinal cortex within 300 ms following stimulus onset. This rhinal process precedes a hippocampal process, which starts about 200 ms later. Further investigation revealed that the rhinal process seems to be a correlate of semantic preprocessing which supports memory formation, whereas the hippocampal process appears to be a correlate of an exclusively mnemonic operation. These studies yielded only indirect evidence for an interaction of rhinal cortex and hippocampus. Direct evidence for a memory related cooperation between both structures, however, has been found in a study analyzing so called gamma activity, EEG oscillations of around 40 Hz. This investigation showed that successful as opposed to unsuccessful memory formation is accompanied by an initial enhancement of rhinal-hippocampal phase synchronization, which is followed by a later desynchronization. Present knowledge about the function of phase synchronized gamma activity suggests that this phase coupling and decoupling initiates and later terminates communication between the two MTL structures. Phase synchronized rhinal-hippocampal gamma activity may, moreover, accomplish Hebbian synaptic modifications and thus provide an initial step of declarative memory formation on the synaptic level.

2021 - ICML
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during the test phase, in the hope of fast adaptation over them. Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation. In this paper, we take one important step further to understand the close connection between these two learning paradigms, through both theoretical analysis and empirical investigation. Theoretically, we first demonstrate that MTL shares the same optimization formulation with a class of gradient-based meta-learning (GBML) algorithms. We then prove that for over-parameterized neural networks with sufficient depth, the learned predictive functions of MTL and GBML are close. In particular, this result implies that the predictions given by these two models are similar over the same unseen task. Empirically, we corroborate our theoretical findings by showing that, with proper implementation, MTL is competitive against state-of-the-art GBML algorithms on a set of few-shot image classification benchmarks. Since existing GBML algorithms often involve costly second-order bi-level optimization, our first-order MTL method is an order of magnitude faster on large-scale datasets such as miniImageNet. We believe this work could help bridge the gap between these two learning paradigms, and provide a computationally efficient alternative to GBML that also supports fast task adaptation. University of Illinois at Urbana-Champaign, Urbana, IL, USA. Correspondence to: Haoxiang Wang <hwang264@illinois.edu>, Han Zhao <hanzhao@illinois.edu>, Bo Li <lbo@illinois.edu>. Proceedings of the 38 th International Conference on Machine Learning, PMLR 139, 2021. Copyright 2021 by the author(s).

2017
Multi-task feature learning by using trace norm regularization

Abstract Multi-task learning can extract the correlation of multiple related machine learning problems to improve performance. This paper considers applying the multi-task learning method to learn a single task. We propose a new learning approach, which employs the mixture of expert model to divide a learning task into several related sub-tasks, and then uses the trace norm regularization to extract common feature representation of these sub-tasks. A nonlinear extension of this approach by using kernel is also provided. Experiments conducted on both simulated and real data sets demonstrate the advantage of the proposed approach.

2018 - ArXiv
Multi-Task Learning with Incomplete Data for Healthcare

Multi-task learning is a type of transfer learning that trains multiple tasks simultaneously and leverages the shared information between related tasks to improve the generalization performance. However, missing features in the input matrix is a much more difficult problem which needs to be carefully addressed. Removing records with missing values can significantly reduce the sample size, which is impractical for datasets with large percentage of missing values. Popular imputation methods often distort the covariance structure of the data, which causes inaccurate inference. In this paper we propose using plug-in covariance matrix estimators to tackle the challenge of missing features. Specifically, we analyze the plug-in estimators under the framework of robust multi-task learning with LASSO and graph regularization, which captures the relatedness between tasks via graph regularization. We use the Alzheimer's disease progression dataset as an example to show how the proposed framework is effective for prediction and model estimation when missing data is present.

2019 - ArXiv
Gumbel-Matrix Routing for Flexible Multi-task Learning

This paper proposes a novel per-task routing method for multi-task applications. Multi-task neural networks can learn to transfer knowledge across different tasks by using parameter sharing. However, sharing parameters between unrelated tasks can hurt performance. To address this issue, we advocate the use of routing networks to learn flexible parameter sharing, where each group of parameters is shared with a different subset of tasks in order to better leverage tasks relatedness. At the same time, it is known that routing networks are notoriously hard to train. We propose the Gumbel-Matrix routing: a novel multi-task routing method, designed to learn fine-grained patterns of parameter sharing. The routing is learned jointly with the model parameters by standard back-propagation thanks to the Gumbel-Softmax trick. When applied to the Omniglot benchmark, the proposed method reduces the state-of-the-art error rate by 17%.

2019 - ACL
A Multi-Task Architecture on Relevance-based Neural Query Translation

We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem with our multi-task learning architecture that achieves 16% improvement over a strong NMT baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm.

2016 - Neurocomputing
HEp-2 cells Classification via clustered multi-task learning

This paper proposes a clustered multi-task learning-based method for automated HEp-2 cells Classification. First, the visual feature is extracted for individual sample to represent its appearance characteristics. Then, the models of multiple HEp-2 cell category are jointly trained in the framework of clustered multi-task learning. The extensive experiments on the HEp 2, cell dataset released by the HEp-2 Cells Classification contest, held at the 2012 International Conference on Patter Recognition, show that the proposed method can discover and share the latent relatedness among multiple tasks and consequently augment the performance. The quantitative comparison against the state-of-the-art methods demonstrates the superiority of the proposed method.

2005 - NIPS
Radial Basis Function Network for Multi-task Learning

We extend radial basis function (RBF) networks to the scenario in which multiple correlated tasks are learned simultaneously, and present the corresponding learning algorithms. We develop the algorithms for learning the network structure, in either a supervised or unsupervised manner. Training data may also be actively selected to improve the network's generalization to test data. Experimental results based on real data demonstrate the advantage of the proposed algorithms and support our conclusions.

2010 - AISTATS
Multi-Task Learning using Generalized t Process

Multi-task learning seeks to improve the generalization performance of a learning task with the help of other related learning tasks. Among the multi-task learning methods proposed thus far, Bonilla et al.’s method (Bonilla et al., 2008) provides a novel multi-task extension of Gaussian process (GP) by using a task covariance matrix to model the relationships between tasks. However, learning the task covariance matrix directly has both computational and representational drawbacks. In this paper, we propose a Bayesian extension by modeling the task covariance matrix as a random matrix with an inverse-Wishart prior and integrating it out to achieve Bayesian model averaging. To make the computation feasible, we first give an alternative weight-space view of Bonilla et al.’s multi-task GP model and then integrate out the task covariance matrix in the model, leading to a multi-task generalized t process (MTGTP). For the likelihood, we use a generalized t noise model which, together with the generalized t process prior, brings about the robustness advantage as well as an analytical form for the marginal likelihood. In order to specify the inverse-Wishart prior, we use the maximum mean discrepancy (MMD) statistic to estimate the parameter matrix of the inverse-Wishart prior. Moreover, we investigate some theoretical properties of MTGTP, such as its asymptotic analysis and learning curve. Comparative experimental studies on two common multi-task learning applications show very promising results. Appearing in Proceedings of the 13 International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, Chia Laguna Resort, Sardinia, Italy. Volume 9 of JMLR: W&CP 9. Copyright 2010 by the authors.

2008 - ECML/PKDD
An Improved Multi-task Learning Approach with Applications in Medical Diagnosis

We propose a family of multi-task learning algorithms for collaborative computer aided diagnosis which aims to diagnose multiple clinically-related abnormal structures from medical images. Our formulations eliminate features irrelevant to all tasks, and identify discriminative features for each of the tasks. A probabilistic model is derived to justify the proposed learning formulations. By equivalence proof, some existing regularization-based methods can also be interpreted by our probabilistic model as imposing a Wishart hyperprior. Convergence analysis highlights the conditions under which the formulations achieve convexity and global convergence. Two real-world medical problems: lung cancer prognosis and heart wall motion analysis, are used to validate the proposed algorithms.

2015 - IEEE Transactions on Multimedia
Multi-Task CNN Model for Attribute Prediction

This paper proposes a joint multi-task learning algorithm to better predict attributes in images using deep convolutional neural networks (CNN). We consider learning binary semantic attributes through a multi-task CNN model, where each CNN will predict one binary attribute. The multi-task learning allows CNN models to simultaneously share visual knowledge among different attribute categories. Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes. In our multi-task framework, we propose a method to decompose the overall model's parameters into a latent task matrix and combination matrix. Furthermore, under-sampled classifiers can leverage shared statistics from other classifiers to improve their performance. Natural grouping of attributes is applied such that attributes in the same group are encouraged to share more knowledge. Meanwhile, attributes in different groups will generally compete with each other, and consequently share less knowledge. We show the effectiveness of our method on two popular attribute datasets.

An Overview of Multi-task Learning

Qiang Yang
|
Yu Zhang
|
Yu Zhang
|
Qiang Yang

Abstract:As a promising area in machine learning, multi-task learning (MTL) aims to improve the performance of multiple related learning tasks by leveraging useful information among them. In this paper, we give an overview of MTL by first giving a definition of MTL. Then several different settings of MTL are introduced, including multi-task supervised learning, multi-task unsupervised learning, multi-task semi-supervised learning, multi-task active learning, multi-task reinforcement learning, multi-task online learning and multi-task multi-view learning. For each setting, representative MTL models are presented. In order to speed up the learning process, parallel and distributed MTL models are introduced. Many areas, including computer vision, bioinformatics, health informatics, speech, natural language processing, web applications and ubiquitous computing, use MTL to improve the performance of the applications involved and some representative works are reviewed. Finally, recent theoretical analyses for MTL are presented.

参考文献

[1]  Ambuj Tewari,et al.  Regularization Techniques for Learning with Matrices , 2009, J. Mach. Learn. Res..

[2]  Jiayu Zhou,et al.  A multi-task learning formulation for predicting disease progression , 2011, KDD.

[3]  Fangzhao Wu,et al.  Collaborative Multi-domain Sentiment Classification , 2015, 2015 IEEE International Conference on Data Mining.

[4]  Jieping Ye,et al.  Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks , 2010, TKDD.

[5]  Alexander J. Smola,et al.  Scalable hierarchical multitask learning algorithms for conversion optimization in display advertising , 2014, WSDM.

[6]  Giuseppe De Nicolao,et al.  Bayesian Online Multitask Learning of Gaussian Processes , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Qiang Yang,et al.  Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico study , 2010, BMC Bioinformatics.

[8]  Tom Heskes,et al.  Task Clustering and Gating for Bayesian Multitask Learning , 2003, J. Mach. Learn. Res..

[9]  Jiayu Zhou,et al.  Integrating low-rank and group-sparse structures for robust multi-task learning , 2011, KDD.

[10]  Massimiliano Pontil,et al.  Convex multi-task feature learning , 2008, Machine Learning.

[11]  Antoni B. Chan,et al.  Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[12]  Min-Ling Zhang,et al.  A Review on Multi-Label Learning Algorithms , 2014, IEEE Transactions on Knowledge and Data Engineering.

[13]  Rich Caruana,et al.  Multitask Learning , 1997, Machine Learning.

[14]  Jieping Ye,et al.  A Multi-Task Learning Formulation for Survival Analysis , 2016, KDD.

[15]  Hui Li,et al.  Multi-task Reinforcement Learning in Partially Observable Stochastic Environments , 2009, J. Mach. Learn. Res..

[16]  Jean-Philippe Vert,et al.  ProDiGe: Prioritization Of Disease Genes with multitask machine learning from positive and unlabeled examples , 2011, BMC Bioinformatics.

[17]  Masashi Sugiyama,et al.  Conic Programming for Multitask Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[18]  Jieping Ye,et al.  Multi-Task Learning for Spatio-Temporal Event Forecasting , 2015, KDD.

[19]  Jieping Ye,et al.  Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis , 2015, IEEE Transactions on Big Data.

[20]  Yu Zhang.  Parallel Multi-task Learning , 2015, 2015 IEEE International Conference on Data Mining.

[21]  Gunnar Rätsch,et al.  Leveraging Sequence Classification by Taxonomy-Based Multitask Learning , 2010, RECOMB.

[22]  Jian Yu,et al.  Saliency Detection by Multitask Sparsity Pursuit , 2012, IEEE Transactions on Image Processing.

[23]  Gang Wang,et al.  Multi-Task CNN Model for Attribute Prediction , 2015, IEEE Transactions on Multimedia.

[24]  Lawrence Carin,et al.  Multi-Task Learning for Classification with Dirichlet Process Priors , 2007, J. Mach. Learn. Res..

[25]  Claudio Gentile,et al.  Linear Algorithms for Online Multitask Classification , 2010, COLT.

[26]  Dit-Yan Yeung,et al.  Multilabel relationship learning , 2013, TKDD.

[27]  Lei Han,et al.  Learning Tree Structure in Multi-Task Learning , 2015, KDD.

[28]  Xiao Lu,et al.  Traffic Sign Recognition via Multi-Modal Tree-Structure Embedded Multi-Task Learning , 2017, IEEE Transactions on Intelligent Transportation Systems.

[29]  Jieping Ye,et al.  Multi-stage multi-task feature learning , 2012, J. Mach. Learn. Res..

[30]  Qiang Yang,et al.  Multitask Learning for Protein Subcellular Location Prediction , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[31]  Xiao-Lei Zhang,et al.  Convex Discriminative Multitask Clustering , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Laxmi Parida,et al.  Novel applications of multitask learning and multiple output regression to multiple genetic trait prediction , 2016, Bioinform..

[33]  Jonathan Baxter,et al.  A Model of Inductive Bias Learning , 2000, J. Artif. Intell. Res..

[34]  Charles A. Micchelli,et al.  Learning Multiple Tasks with Kernel Methods , 2005, J. Mach. Learn. Res..

[35]  Gunnar Rätsch,et al.  Inferring latent task structure for Multitask Learning by Multiple Kernel Learning , 2010, BMC Bioinformatics.

[36]  Yu Zhang,et al.  Learning Inverse Dynamics by Gaussian process Begrression under the Multi-Task Learning Framework , 2009 .

[37]  Dit-Yan Yeung,et al.  A Regularization Approach to Learning Task Relationships in Multitask Learning , 2014, ACM Trans. Knowl. Discov. Data.

[38]  Philip M. Long,et al.  Online Learning of Multiple Tasks with a Shared Loss , 2007, J. Mach. Learn. Res..

[39]  Tong Zhang,et al.  A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , 2005, J. Mach. Learn. Res..

[40]  Bahram Parvin,et al.  Sparse multitask regression for identifying common mechanism of response to therapeutic targets , 2010, Bioinform..

[41]  Andreas Maurer,et al.  Bounds for Linear Multi-Task Learning , 2006, J. Mach. Learn. Res..

[42]  Paul Tseng,et al.  Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning , 2010, SIAM J. Optim..

[43]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[44]  Jieping Ye,et al.  Feature Constrained Multi-Task Learning Models for Spatiotemporal Event Forecasting , 2017, IEEE Transactions on Knowledge and Data Engineering.

[45]  Yu Zhang,et al.  A Survey on Multi-Task Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[46]  Dit-Yan Yeung,et al.  Semi-Supervised Multi-Task Regression , 2009, ECML/PKDD.

[47]  Hui Li,et al.  Semisupervised Multitask Learning , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Ya Zhang,et al.  Multi-task learning for boosting with application to web search ranking , 2010, KDD.

[49]  Raymond J. Mooney,et al.  Active Multitask Learning Using Both Latent and Supervised Shared Topics , 2014, SDM.

[50]  Eric P. Xing,et al.  Multi-population GWA mapping via multi-task regularized regression , 2010, Bioinform..

[51]  Ben Taskar,et al.  Joint covariate selection and joint subspace selection for multiple classification problems , 2010, Stat. Comput..

[52]  Narendra Ahuja,et al.  Robust Visual Tracking via Structured Multi-Task Sparse Learning , 2012, International Journal of Computer Vision.

引用
Multi-task Learning for Multilingual Neural Machine Translation
EMNLP
2020
Enhancing Transformer with Sememe Knowledge
RepL4NLP@ACL
2020
Gradient Surgery for Multi-Task Learning
NeurIPS
2020
Multi-Task Learning for Sequence Tagging: An Empirical Study
COLING
2018
Unfairness Discovery and Prevention For Few-Shot Regression
2020 IEEE International Conference on Knowledge Graph (ICKG)
2020
A Joint Named-Entity Recognizer for Heterogeneous Tag-setsUsing a Tag Hierarchy
ACL
2019
Personalized Attraction Enhanced Sponsored Search with Multi-task Learning
KDD
2019
MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2020
Feature Fusion-Based Multi-Task ConvNet for Simultaneous Optical Performance Monitoring and Bit-Rate/Modulation Format Identification
IEEE Access
2019
Hypothesis Disparity Regularized Mutual Information Maximization
AAAI
2020
Single-Network Whole-Body Pose Estimation
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
2019
Learning an Interpretable Graph Structure in Multi-Task Learning
ArXiv
2020
Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3
Neural Comput. Appl.
2020
Named Entities in Medical Case Reports: Corpus and Experiments
LREC
2020
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
ACL
2020
Blind Backdoors in Deep Learning Models
USENIX Security Symposium
2020
The Natural Language of Actions
ICML
2019
Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
MIDL
2020
Deep Reinforcement Learning
Reinforcement Learning for Cyber-Physical Systems
2018
Overton: A Data System for Monitoring and Improving Machine-Learned Products
CIDR
2019