To address the challenging low-resource non-topical text classification problems in domain specific settings we introduce ContextGen – a novel approach that uses targeted text generation with no fine tuning to augment the available small annotated dataset. It first adapts the powerful GPT-2 text generation model to generate samples relevant for the domain by using properly designed context text as input for generation. Then it assigns class labels to the newly generated samples after which they are added to the initial training set. We demonstrate the superior performance of a state-of-the-art text classifier trained with the augmented labelled dataset for four different non-topical tasks in the low resource setting, three of which are from specialized domains.

Large scale, multi-label text datasets with high numbers of different classes are expensive to annotate, even more so if they deal with domain specific language. In this work, we aim to build classifiers on these datasets using Active Learning in order to reduce the labeling effort. We outline the challenges when dealing with extreme multi-label settings and show the limitations of existing Active Learning strategies by focusing on their effectiveness as well as efficiency in terms of computational cost. In addition, we present five multi-label datasets which were compiled from hierarchical classification tasks to serve as benchmarks in the context of extreme multi-label classification for future experiments. Finally, we provide insight into multi-class, multi-label evaluation and present an improved classifier architecture on top of pre-trained transformer language models.

State-of-the-art approaches to reasoning and question answering over knowledge graphs (KGs) usually scale with the number of edges and can only be applied effectively on small instance-dependent subgraphs. In this paper, we address this issue by showing that multi-hop and more complex logical reasoning can be accomplished separately without losing expressive power. Motivated by this insight, we propose an approach to multi-hop reasoning that scales linearly with the number of relation types in the graph, which is usually significantly smaller than the number of edges or nodes. This produces a set of candidate solutions that can be provably refined to recover the solution to the original problem. Our experiments on knowledge-based question answering show that our approach solves the multi-hop MetaQA dataset, achieves a new state-of-the-art on the more challenging WebQuestionsSP, is orders of magnitude more scalable than competitive approaches, and can achieve compositional generalization out of the training distribution.

Technology refresh is an important component in data-center management that needs to be properly justified because of its high cost and associated migration risk. The goal of this paper is to support the technology refresh decision process for small target IT environments with a statistical learning method that automatically identifies and ranks their servers with problematic behavior based on incident ticket and server attribute data. Since the IT environments are heterogeneous, in practice, a separate model is trained for each of them. To address the small sample sizes available for many IT environments, we develop a random forest transfer learning solution that leverages information from large IT environments in a selective manner. It trains a model for each target IT environment that uses properly derived resampling weights such that the distribution of the pool of all examples from the large accounts is matched to the target distribution of the small target IT environment. In this way, a tailored predictive model that uses the information available from many large IT environments provides good quality predictions for small IT environments. We demonstrate the superior prediction quality of our model on a large set of real data.

Disks are among the most frequently failing components in today's IT environments. Despite a set of defense mechanisms such as RAID, the availability and reliability of the system are still often impacted severely. In this paper, we present a highly accurate SMART-based analysis pipeline that can correctly predict the necessity of a disk replacement even 10-15 days in advance. Our method has been built and evaluated on more than 30000 disks from two major manufacturers, monitored over 17 months. Our approach employs statistical techniques to automatically detect which SMART parameters correlate with disk replacement and uses them to predict the replacement of a disk with even 98% accuracy.

We present a novel technique that optimizes the dispatching of incident tickets to the agents in an IT Service Support Environment. Unlike the common skill-based dispatching, our approach also takes empirical evidence on the agent's speed from historical data into account. Our solution consists of two parts. First, a novel technique clusters historic tickets into incident categories that are discriminative in terms of agent's performance. Second, a dispatching policy selects, for an incoming ticket, the fastest available agent according to the target cluster. We show that, for ticket data collected from several Service Delivery Units, our new dispatching technique can reduce service time between $35\%$ and $44\%$.

A company's IT infrastructure delivers the basic hardware, networking, operating system, and middleware support to the business' applications. IT service providers perform incident and problem resolution, as well as user administration and change implementation required to maintain the availability and service provided for the business. As a result, they become increasingly challenged with delivering better, faster, and cheaper services to their customers. With the variety of incident tickets reported on a daily basis, understanding where and how much effort is spent to resolve them is critical. Moreover, analyzing the effort data identifies opportunities for self-service and automation, as well as what modernization strategies businesses should implement to reduce incident volumes and, by association, labor effort. In this paper, we conduct a large scale study on the incident and server factors that affect technician effort and quantify their impact. We show that the nature of the incidents and their complexity, the assigned support groups, as well as the underlying OS type play a major role in how much labor effort is spent towards resolving such tickets.

We present a new methodology for solving linear Support Vector Machines (SVMs) that capitalizes on multiple 1D projections. We show that the approach approximates the optimal solution with high accuracy and comes with analytical guarantees. Our solution adapts on methodologies from random projections, exponential search, and coordinate descent. In our experimental evaluation, we compare our approach with the popular liblinear SVM library. We demonstrate a significant speedup on various benchmarks. At the same time, the new methodology provides a comparable or better approximation factor of the optimal solution and exhibits smooth convergence properties. Our results are accompanied by bounds on the time complexity and accuracy.

In this paper, we introduce a novel approach for incident ticket classification that aims at minimizing the manual labelling effort while achieving good-quality predictions. To accomplish this, we devise a two-stage technique that employs hierarchical clustering using a combination of graph clustering (community finding) and topic modelling as first stage, followed by either another round of hierarchical clustering or an active learning approach as second stage. We evaluate the performance of our method in terms of manual labelling effort, prediction quality and efficiency on three real-world datasets and demonstrate that classical approaches to text classification are not well suited for incident ticket texts.

Technology refresh is an important component in data center management. The goal of this paper is to assess the impact of HW and OS currency on server availability based on a large set of incident tickets and server attributes data collected from several different IT environments. In order to achieve this we first identify the server failure incidents using a machine learning method for automatic ticket classification. Then we conduct the data analysis to inspect the impact of HW and OS type along with their currency on the rates of server failures. This can further be used to derive guidelines to support the technology refresh decisions in the data centers.

Today the decision of when to modernize which elements of the server HW/SW stack is often done manually based on simple business rules. In this paper we alleviate this problem by supporting the decision process with an automated approach based on incident tickets and server attributes data. As a first step we identify and rank servers with problematic behavior as candidates for modernization using a random forest classifier. Second, this predictive model is used to evaluate the impact of different modernization actions and suggest the most effective ones. We show that our chosen model yields high quality predictions and outperforms traditional linear regression models on a large set of real data.

This paper presents an approach that predicts the effectiveness of HIV combination therapies by simultaneously addressing several problems affecting the available HIV clinical data sets: the different treatment backgrounds of the samples, the uneven representation of the levels of therapy experience, the missing treatment history information, the uneven therapy representation and the unbalanced therapy outcome representation. The computational validation on clinical data shows that, compared to the most commonly used approach that does not account for the issues mentioned above, our model has significantly higher predictive power. This is especially true for samples stemming from patients with longer treatment history and samples associated with rare therapies. Furthermore, our approach is at least as powerful for the remaining samples.

MOTIVATION: As there exists no cure or vaccine for the infection with human immunodeficiency virus (HIV), the standard approach to treating HIV patients is to repeatedly administer different combinations of several antiretroviral drugs. Because of the large number of possible drug combinations, manually finding a successful regimen becomes practically impossible. This presents a major challenge for HIV treatment. The application of machine learning methods for predicting virological responses to potential therapies is a possible approach to solving this problem. However, due to evolving trends in treating HIV patients the available clinical datasets have a highly unbalanced representation, which might negatively affect the usefulness of derived statistical models. RESULTS: This article presents an approach that tackles the problem of predicting virological response to combination therapies by learning a separate logistic regression model for each therapy. The models are fitted by using not only the data from the target therapy but also the information from similar therapies. For this purpose, we introduce and evaluate two different measures of therapy similarity. The models are also able to incorporate phenotypic knowledge on the therapy outcomes through a Gaussian prior. With our approach we balance the uneven therapy representation in the datasets and produce higher quality models for therapies with very few training samples. According to the results from the computational experiments our therapy similarity model performs significantly better than training separate models for each therapy by using solely their examples. Furthermore, the model's performance is as good as an approach that encodes therapy information in the input feature space with the advantage of delivering better results for therapies with very few training samples. AVAILABILITY: Code of the efficient logistic regression is available from http://www.mpi-inf.mpg.de/%7Ejasmina/fastLogistic.zip.

We address the problem of learning classifiers for a large number of tasks. We derive a solution that produces resampling weights which match the pool of all examples to the target distribution of any given task. Our work is motivated by the problem of predicting the outcome of a therapy attempt for a patient who carries an HIV virus with a set of observed genetic properties. Such predictions need to be made for hundreds of possible combinations of drugs, some of which use similar biochemical mechanisms. Multi-task learning enables us to make predictions even for drug combinations with few or no training examples and substantially improves the overall prediction accuracy.

Abstract Summary: In genetics, many evolutionary pathways can be modeled by the ordered accumulation of permanent changes. Mixture models of mutagenetic trees have been used to describe disease progression in cancer and in HIV. In cancer, progression is modeled by the accumulation of chromosomal gains and losses in tumor cells; in HIV, the accumulation of drug resistance-associated mutations in the viral genome is known to be associated with disease progression. From such evolutionary models, genetic progression scores can be derived that assign measures for the disease state to single patients. Rtreemix is an R package for estimating mixture models of evolutionary pathways from observed cross-sectional data and for estimating associated genetic progression scores. The package also provides extended functionality for estimating confidence intervals for estimated model parameters and for evaluating the stability of the estimated evolutionary mixture models. Availability: Rtreemix is an R package that is freely available from the Bioconductor project at http://www.bioconductor.org and runs on Linux and Windows. Contact: [email protected]

BACKGROUND: Mixture models of mutagenetic trees are evolutionary models that capture several pathways of ordered accumulation of genetic events observed in different subsets of patients. They were used to model HIV progression by accumulation of resistance mutations in the viral genome under drug pressure and cancer progression by accumulation of chromosomal aberrations in tumor cells. From the mixture models a genetic progression score (GPS) can be derived that estimates the genetic status of single patients according to the corresponding progression along the tree models. GPS values were shown to have predictive power for estimating drug resistance in HIV or the survival time in cancer. Still, the reliability of the exact values of such complex markers derived from graphical models can be questioned. RESULTS: In a simulation study, we analyzed various aspects of the stability of estimated mutagenetic trees mixture models. It turned out that the induced probabilistic distributions and the tree topologies are recovered with high precision by an EM-like learning algorithm. However, only for models with just one major model component, also GPS values of single patients can be reliably estimated. CONCLUSION: It is encouraging that the estimation process of mutagenetic trees mixture models can be performed with high confidence regarding induced probability distributions and the general shape of the tree topologies. For a model with only one major disease progression process, even genetic progression scores for single patients can be reliably estimated. However, for models with more than one relevant component, alternative measures should be introduced for estimating the stage of disease progression.