Lifelong multitask learning is a multitask learning framework in which a learning agent faces the tasks that need to be learnt in an online manner. Lifelong multitask learning framework may be applied to a variety of applications such as image annotation, robotics, automated machines etc, and hence, may prove to be a highly promising direction for further investigation. However, the lifelong learning framework comes with its own baggage of challenges. The biggest challenge is the fact that the characteristics of the future tasks which might be encountered by the learning agents are entirely unknown. If all the tasks are assumed to be related, there may be a risk of training from unrelated task resulting in negative transfer of information. To overcome this problem, both batch and online multitask learning algorithms learn task relationships. However, due to the unknown nature of the future tasks, learning the task relationships is also difficult in lifelong multitask learning. In this paper, we propose learning functions to model the task relationships as it is computationally cheaper in an online setting. More specifically, we learn partition functions in the task space to divide the tasks into cluster. Our major contribution is to present a global formulation to learn both the task partitions and the parameters. We provide a supervised learning framework to estimate both the partition function and the model. The current method has been implemented and compared against other leading lifelong learning algorithms using several real world datasets, and we show that the current method has a superior performance.

Multitask learning has been thoroughly proven to improve the generalization performance given a set of related tasks. Most multitask learning algorithm assume that all tasks are related. However, if all the tasks are not related, negative transfer of information occurs amongst the tasks, and the performance of traditional multitask learning algorithm worsens. Thus, we design an algorithm that simultaneously groups the related tasks and trains only the related task together. There are different approaches to train the related tasks in multi-task learning based on which information is shared across the tasks. These approaches either assume that the parameters of each of the tasks are situated close together, or assume that there is a common underlying latent space in the features of the tasks that is related. Most multi-task learning algorithm use either regularization method or matrix-variate priors. In our algorithm, the related tasks are tied together by a set of common features selected by each tasks. Thus, to train the related tasks together, we use spike and slab prior to select a common set of features for the related tasks, and a mixture of gaussians prior to select the set of related tasks. For validation, the developed algorithm is tested on toxicity prediction and hand written digit recognition data sets. The results show a significant improvement over multitask learning with feature selection for larger number of tasks. Further, the developed algorithm is also compared against another state of the art algorithm that similarly groups the related tasks together and proven to be better and more accurate.

Recently, graph representations of text have been showing improved performance over conventional bag-of-words representations in text categorization applications. In this paper, we present a graph-based representation for biomedical articles and use graph kernels to classify those articles into high-level categories. In our representation, common biomedical concepts and semantic relationships are identified with the help of an existing ontology and are used to build a rich graph structure that provides a consistent feature set and preserves additional semantic information that could improve a classifier's performance. We attempt to classify the graphs using both a set-based graph kernel that is capable of dealing with the disconnected nature of the graphs and a simple linear kernel. Finally, we report the results comparing the classification performance of the kernel classifiers to common text-based classifiers.

Effectively utilizing readily available auxiliary data to improve predictive performance on new modeling tasks is a key problem in data mining. In this research, the goal is to transfer knowledge between sources of data, particularly when ground-truth information for the new modeling task is scarce or is expensive to collect where leveraging any auxiliary sources of data becomes a necessity. Toward seamless knowledge transfer among tasks, effective representation of the data is a critical but yet not fully explored research area for the data engineer and data miner. Here, we present a technique based on the idea of sparse coding, which essentially attempts to find an embedding for the data by assigning feature values based on subspace cluster membership. We modify the idea of sparse coding by focusing the identification of shared clusters between data when source and target data may have different distributions. In our paper, we point out cases where a direct application of sparse coding will lead to a failure of knowledge transfer. We then present the details of our extension to sparse coding, by incorporating distribution distance estimates for the embedded data, and show that the proposed algorithm can overcome the shortcomings of the sparse coding algorithm on synthetic data and achieve improved predictive performance on a real world chemical toxicity transfer learning task.

A major concern across the globe is the growing number of new chemicals that are brought to use on a regular basis without having any knowledge about their toxic behavior. The challenge here is that the growth in the number of chemicals is fast, and the traditional standards for toxicity testing involve a slow and expensive process of in vivo animal testing. Hence, a number of attempts are being made to find alternate methods of toxicity testing. In this paper we explore Bayesian classifiers and show that if we approximate posterior in the Bayesian classifier with specially crafted basis functions, we can improve upon the performance. We have tested our methods using data sets from the Environmental Protection Agency (EPA). Our experimental study demonstrated the utility of the advanced Bayesian classification approach.

Effectively utilizing readily available auxiliary data to improve predictive performance on new modeling tasks is a key problem in data mining. In this research the goal is to transfer knowledge between sources of data, particularly when ground truth information for the new modeling task is scarce or is expensive to collect where leveraging any auxiliary sources of data becomes a necessity. Towards seamless knowledge transfer among tasks, effective representation of the data is a critical but yet not fully explored research area for the data engineer and data miner. Here we present a technique based on the idea of sparse coding, which essentially attempts to find an embedding for the data by assigning feature values based on subspace cluster membership. We modify the idea of sparse coding by focusing the identification of shared clusters between data when source and target data may have different distributions. In our paper, we point out cases where a direct application of sparse coding will lead to a failure of knowledge transfer. We then present the details of our extension to sparse coding, by incorporating distribution distance estimates for the embedded data, and show that the proposed algorithm can overcome the shortcomings of the sparse coding algorithm on synthetic data and achieve improved predictive performance on a real world chemical toxicity transfer learning task.

As the number of new chemicals developed and being used keep adding every year, having the toxic profiles of each chemical becomes a daunting challenge. To meet this information gap, EPA suggested that certain in vitro assays and computational methods, which predict toxicity related information in much lesser time and cost than traditional in vivo methods, may be used. In this paper, we use computational techniques to use results from certain in vitro assays applied on 309 chemicals (whose toxicity profile is readily available) along with the molecular descriptors and other computed physical-chemical properties of the chemicals to predict the toxicity caused by chemical at a particular endpoint. The dataset is available from EPA TOXCAST group online. We show that Random Forest and Naïve Bayes have a good performance on this dataset. We also show that using small and related trees in random forest help to further improve the performance.