Distance metric learning algorithms aim to learn how to measure similarities between data objects in a metric space. In the context of clustering, metric learning typically relies on side-information provided by experts, most commonly expressed in the form of pairwise constraints. In this setting, algorithms for metric learning execute data transformations that bring pairs of data points involved in must-link constraints close together, whereas pair of points involved in cannot-link constraints are moved away from each other. One caveat to such methods is that they can considerably change the original data distribution properties. With that in mind, we propose a Lagrangian-based approach to assist distance metric learning algorithms for clustering. Our method is developed to identify the least impactful transformations to the original data space, while still learning a more suitable metric space for grouping the data using the provided side information. Our results demonstrate that the proposed methodology is able to achieve a competitive clustering performance with respect to truth classification. Furthermore, the method is able to provide more accurate views of the transformed datasets, which can lead to more reliable clustering interpretations.

In software projects, applications are often monitored by systems that automatically identify crashes, collect their information into reports, and submit them to developers. Especially in popular applications, such systems tend to generate a large number of crash reports in which a significant portion of them are duplicate. Due to this high submission volume, in practice, the crash report deduplication is supported by devising automatic systems whose efficiency is a critical constraint. In this paper, we focus on improving deduplication system throughput by speeding up the stack trace comparison. In contrast to the state-of-the-art techniques, we propose FaST, a novel sequence alignment method that computes the similarity score between two stack traces in linear time. Our method independently aligns identical frames in two stack traces by means of a simple alignment heuristic. We evaluate FaST and five competing methods on four datasets from open-source projects using ranking and binary metrics. Despite its simplicity, FaST consistently achieves state-of-the-art performance regarding all metrics considered. Moreover, our experiments confirm that FaST is substantially more efficient than methods based on optimal sequence alignment.

Kernel traces are sequences of low-level events comprising a name and multiple arguments, including a timestamp, a process id, and a return value, depending on the event. Their analysis helps uncover intrusions, identify bugs, and find latency causes. However, their effectiveness is hindered by omitting the event arguments. To remedy this limitation, we introduce a general approach to learning a representation of the event names along with their arguments using both embedding and encoding. The proposed method is readily applicable to most neural networks and is task-agnostic. The benefit is quantified by conducting an ablation study on three groups of arguments: call-related, process-related, and time-related. Experiments were conducted on a novel web request dataset and validated on a second dataset collected on pre-production servers by Ciena, our partnering company. By leveraging additional information, we were able to increase the performance of two widely-used neural networks, an LSTM and a Transformer, by up to 11.3% on two unsupervised language modelling tasks. Such tasks may be used to detect anomalies, pre-train neural networks to improve their performance, and extract a contextual representation of the events.

Bug tracking systems (BTS) are widely used in software projects. An important task in such systems consists of identifying duplicate bug reports, i.e., distinct reports related to the same software issue. For several reasons, reporting bugs that have already been reported is quite frequent, making their manual triage impractical in large BTSs. In this paper, we present a novel deep learning network based on soft-attention alignment to improve duplicate bug report detection. For a given pair of possibly duplicate reports, the attention mechanism computes interdependent representations for each report, which is more powerful than previous approaches. We evaluate our model on four well-known datasets derived from BTSs of four popular open-source projects. Our evaluation is based on a ranking-based metric, which is more realistic than decision-making metrics used in many previous works. Achieved results demonstrate that our model outperforms state-of-the-art systems and strong baselines in different scenarios. Finally, an ablation study is performed to confirm that the proposed architecture improves the duplicate bug reports detection.

Predicting locational choices (i.e., where one chooses to sit) is a challenging task because preferences are highly heterogeneous and depend not only on the location of the seats in the environment but also on the location of others. In the present research, we propose RecSeats - a framework to predict locational choices. The framework augments individual-level discrete choice models with a convolutional neural network (CNN) which can capture higher order interactions between features of available seats. The framework is flexible and can accommodate complexity in real-world locational choice data such as variability in the number of tickets purchased and the number and locations from past purchases. Applied to both locational choice experiment data and to ticketing data from a large North-American concert hall, we show that augmenting individual-level discrete choice models with a CNN consistently provides strong predictive accuracy.

Bike sharing systems continue gaining worldwide popularity as they offer benefits on various levels, from society to environment. Given that those systems tend to be unbalanced along time, bikes are typically redistributed throughout the day to better meet the demand. Reasonably accurate demand prediction is key to effective redistribution; however, it is has received only little attention in the literature. In this paper, we focus on predicting the hourly demand for demand rentals and returns at each station of the system. The proposed model uses temporal and weather features to predict demand mean and variance. It first extracts the main traffic behaviors from the stations. These simplified behaviors are then predicted and used to perform station-level predictions based on machine learning and statistical inference techniques. We then focus on determining decision intervals, which are often used by bike sharing companies for their online rebalancing operations. Our models are validated on a two-year period of real data from BIXI Montréal. A worst-case analysis suggests that the intervals generated by our models may decrease unsatisfied demands by 30% when compared to the current methodology employed in practice.