Multi-task learning using shared and task specific information

Multi-task learning solves multiple related learning problems simultaneously by sharing some common structure for improved generalization performance of each task. We propose a novel approach to multi-task learning which captures task similarity through a shared basis vector set. The variability across tasks is captured through task specific basis vector set. We use sparse support vector machine (SVM) algorithm to select the basis vector sets for the tasks. The approach results in a sparse model where the prediction is done using very few examples. The effectiveness of our approach is demonstrated through experiments on synthetic and real multi-task datasets.

Factorial multi-task learning : a Bayesian nonparametric approach

Multi-task learning is a paradigm shown to improve the performance of related tasks through their joint learning. However, for real-world data, it is usually difficult to assess the task relatedness and joint learning with unrelated tasks may lead to serious performance degradations. To this end, we propose a framework that groups the tasks based on their relatedness in a subspace and allows a varying degree of relatedness among tasks by sharing the subspace bases across the groups. This provides the flexibility of no sharing when two sets of tasks are unrelated and partial/total sharing when the tasks are related. Importantly, the number of task-groups and the subspace dimensionality are automatically inferred from the data. To realize our framework, we introduce a novel Bayesian nonparametric prior that extends the traditional hierarchical beta process prior using a Dirichlet process to permit potentially infinite number of child beta processes. We apply our model for multi-task regression and classification applications. Experimental results using several synthetic and real datasets show the superiority of our model to other recent multi-task learning methods. Copyright 2013 by the author(s).

Collaborating differently on different topics: a multi-relational approach to multi-task learning

Multi-task learning offers a way to benefit from synergy of multiple related prediction tasks via their joint modeling. Current multi-task techniques model related tasks jointly, assuming that the tasks share the same relationship across features uniformly. This assumption is seldom true as tasks may be related across some features but not others. Addressing this problem, we propose a new multi-task learning model that learns separate task relationships along different features. This added flexibility allows our model to have a finer and differential level of control in joint modeling of tasks along different features. We formulate the model as an optimization problem and provide an efficient, iterative solution. We illustrate the behavior of the proposed model using a synthetic dataset where we induce varied feature-dependent task relationships: positive relationship, negative relationship, no relationship. Using four real datasets, we evaluate the effectiveness of the proposed model for many multi-task regression and classification problems, and demonstrate its superiority over other state-of-the-art multi-task learning models

A new transfer learning framework with application to model-agnostic multi-task learning

Learning from small number of examples is a challenging problem in machine learning. An effective way to improve the performance is through exploiting knowledge from other related tasks. Multi-task learning (MTL) is one such useful paradigm that aims to improve the performance through jointly modeling multiple related tasks. Although there exist numerous classification or regression models in machine learning literature, most of the MTL models are built around ridge or logistic regression. There exist some limited works, which propose multi-task extension of techniques such as support vector machine, Gaussian processes. However, all these MTL models are tied to specific classification or regression algorithms and there is no single MTL algorithm that can be used at a meta level for any given learning algorithm. Addressing this problem, we propose a generic, model-agnostic joint modeling framework that can take any classification or regression algorithm of a practitioner’s choice (standard or custom-built) and build its MTL variant. The key observation that drives our framework is that due to small number of examples, the estimates of task parameters are usually poor, and we show that this leads to an under-estimation of task relatedness between any two tasks with high probability. We derive an algorithm that brings the tasks closer to their true relatedness by improving the estimates of task parameters. This is achieved by appropriate sharing of data across tasks. We provide the detail theoretical underpinning of the algorithm. Through our experiments with both synthetic and real datasets, we demonstrate that the multi-task variants of several classifiers/regressors (logistic regression, support vector machine, K-nearest neighbor, Random Forest, ridge regression, support vector regression) convincingly outperform their single-task counterparts. We also show that the proposed model performs comparable or better than many state-of-the-art MTL and transfer learning baselines.

What shall i share and with whom? A multi-task learning formulation using multi-faceted task relationships

Multi-task learning is a learning paradigm that improves the performance of "related" tasks through their joint learning. To do this each task answers the question "Which other task should I share with"? This task relatedness can be complex - a task may be related to one set of tasks based on one subset of features and to other tasks based on other subsets. Existing multi-task learning methods do not explicitly model this reality, learning a single-faceted task relationship over all the features. This degrades performance by forcing a task to become similar to other tasks even on their unrelated features. Addressing this gap, we propose a novel multi-task learning model that leams multi-faceted task relationship, allowing tasks to collaborate differentially on different feature subsets. This is achieved by simultaneously learning a low dimensional sub-space for task parameters and inducing task groups over each latent subspace basis using a novel combination of L1 and pairwise L∞ norms. Further, our model can induce grouping across both positively and negatively related tasks, which helps towards exploiting knowledge from all types of related tasks. We validate our model on two synthetic and five real datasets, and show significant performance improvements over several state-of-the-art multi-task learning techniques. Thus our model effectively answers for each task: What shall I share and with whom?

Differentially private multi-task learning

Privacy restrictions of sensitive data repositories imply that the data analysis is performed in isolation at each data source. A prime example is the isolated nature of building prognosis models from hospital data and the associated challenge of dealing with small number of samples in risk classes (e.g. suicide) while doing so. Pooling knowledge from other hospitals, through multi-task learning, can alleviate this problem. However, if knowledge is to be shared unrestricted, privacy is breached. Addressing this, we propose a novel multi-task learning method that preserves privacy of data under the strong guarantees of differential privacy. Further, we develop a novel attribute-wise noise addition scheme that significantly lifts the utility of the proposed method. We demonstrate the effectiveness of our method with a synthetic and two real datasets.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

Prediciton of emergency events: a multi-task multi-label learning approach

Prediction of patient outcomes is critical to plan resources in an hospital emergency department. We present a method to exploit longitudinal data from Electronic Medical Records (EMR), whilst exploiting multiple patient outcomes. We divide the EMR data into segments where each segment is a task, and all tasks are associated with multiple patient outcomes over a 3, 6 and 12 month period. We propose a model that learns a prediction function for each task-label pair, interacting through two subspaces: the first subspace is used to impose sharing across all tasks for a given label. The second subspace captures the task-specific variations and is shared across all the labels for a given task. The proposed model is formulated as an iterative optimization problems and solved using a scalable and efficient Block co-ordinate descent (BCD) method. We apply the proposed model on two hospital cohorts - Cancer and Acute Myocardial Infarction (AMI) patients collected over a two year period from a large hospital emergency department. We show that the predictive performance of our proposed models is significantly better than those of several state-of-the-art multi-task and multi-label learning methods.

Toxicity prediction in cancer using multiple instance learning in a multi-task framework

Treatments of cancer cause severe side effects called toxicities. Reduction of such effects is crucial in cancer care. To impact care, we need to predict toxicities at fortnightly intervals. This toxicity data differs from traditional time series data as toxicities can be caused by one treatment on a given day alone, and thus it is necessary to consider the effect of the singular data vector causing toxicity. We model the data before prediction points using the multiple instance learning, where each bag is composed of multiple instances associated with daily treatments and patient-specific attributes, such as chemotherapy, radiotherapy, age and cancer types. We then formulate a Bayesian multi-task framework to enhance toxicity prediction at each prediction point. The use of the prior allows factors to be shared across task predictors. Our proposed method simultaneously captures the heterogeneity of daily treatments and performs toxicity prediction at different prediction points. Our method was evaluated on a real-word dataset of more than 2000 cancer patients and had achieved a better prediction accuracy in terms of AUC than the state-of-art baselines.

Response threshold models and stochastic learning automata for self-coordination of heterogeneous multi-task distribution in multi-robot systems.

This paper focuses on the general problem of coordinating multiple robots. More specifically, it addresses the self-selection of heterogeneous specialized tasks by autonomous robots. In this paper we focus on a specifically distributed or decentralized approach as we are particularly interested in a decentralized solution where the robots themselves autonomously and in an individual manner, are responsible for selecting a particular task so that all the existing tasks are optimally distributed and executed. In this regard, we have established an experimental scenario to solve the corresponding multi-task distribution problem and we propose a solution using two different approaches by applying Response Threshold Models as well as Learning Automata-based probabilistic algorithms. We have evaluated the robustness of the algorithms, perturbing the number of pending loads to simulate the robot’s error in estimating the real number of pending tasks and also the dynamic generation of loads through time. The paper ends with a critical discussion of experimental results.

Multi-task transfer learning for in hospital-death prediction for ICU patients

Multi-Task Transfer Learning (MTTL) is an efficient approach for learning from inter-related tasks with small sample size and imbalanced class distribution. Since the intensive care unit (ICU) data set (publicly available in Physionet) has subjects from four different ICU types, we hypothesizethat there is an underlying relatedness amongst various ICU types. Therefore, this study aims to explore MTTL model for in-hospital mortality prediction of ICU patients. We used singletask learning (STL) approach on the augmented data as well as individual ICU data and compared the performance with the proposed MTTL model. As a performance measurement metrics, we used sensitivity (Sens), positive predictivity (+Pred), and Score. MTTL with class balancing showed the best performance with score of 0.78, 0.73, o.52 and 0.63 for ICU type 1(Coronary care unit), 2 (Cardiac surgery unit), 3 (Medical ICU) and 4 (Surgical ICU) respectively. In contrast the maximum score obtained using STL approach was 0.40 for ICU type 1 & 2. These results indicates that the performance of in-hospital mortality can be improved using ICU type information and by balancing the ’non-survivor’ class. The findings of the study may be useful for quantifying the quality of ICU care, managing ICU resources and selecting appropriate interventions.

Beyond dataset bias: Multi-task unaligned shared knowledge transfer

Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new multiclass problem. Our main idea is to identify an image representation that decomposes orthogonally into two subspaces: a part specific to each dataset, and a part generic to, and therefore shared between, all the considered source sets. This allows us to use the generic representation as un-biased reference knowledge for a novel classification task. By casting the method in the multi-view setting, we also make it possible to use different features for different databases. We call the algorithm MUST, Multitask Unaligned Shared knowledge Transfer. Through extensive experiments on five public datasets, we show that MUST consistently improves the cross-datasets generalization performance. © 2013 Springer-Verlag.

Multi-apprentice learning for meta-heuristics parameter tuning in a multi agent scheduling system

The scheduling problem is considered in complexity theory as a NP-hard combinatorial optimization problem. Meta-heuristics proved to be very useful in the resolution of this class of problems. However, these techniques require parameter tuning which is a very hard task to perform. A Case-based Reasoning module is proposed in order to solve the parameter tuning problem in a Multi-Agent Scheduling System. A computational study is performed in order to evaluate the proposed CBR module performance.

Multiple task transfer learning with small sample sizes

Prognosis, such as predicting mortality, is common in medicine. When confronted with small numbers of samples, as in rare medical conditions, the task is challenging. We propose a framework for classification with data with small numbers of samples. Conceptually, our solution is a hybrid of multi-task and transfer learning, employing data samples from source tasks as in transfer learning, but considering all tasks together as in multi-task learning. Each task is modelled jointly with other related tasks by directly augmenting the data from other tasks. The degree of augmentation depends on the task relatedness and is estimated directly from the data. We apply the model on three diverse real-world data sets (healthcare data, handwritten digit data and face data) and show that our method outperforms several state-of-the-art multi-task learning baselines. We extend the model for online multi-task learning where the model parameters are incrementally updated given new data or new tasks. The novelty of our method lies in offering a hybrid multi-task/transfer learning model to exploit sharing across tasks at the data-level and joint parameter learning.