SEMLA is sponsoring travel grants for students attending the event. On a competitive basis, SEMLA 2023 offers travel grants to students outside of Montreal who have an accepted poster or research talk at the event. This program will support up to 10 students, and travel expenses of up to 500 CAD per individual will be provided. The grants will enable sharing of scientific information and stimulate research interests for students in the fields of software engineering and machine learning.
Eligibility criteria:
- An applicant must be an undergraduate/graduate student who has an poster or research talk accepted to be presented at SEMLA 2023.
- The applicant must justify the travel expenses related to SEMLA. Allowable expenses include economy airfare, local transportation, and hotel. Reimbursement will require receipts.
Application Deadline: May 15, 2023
Acceptance Notification: May 18, 2023 April 05, 2023
How to Apply:
Interested students must complete the online application form by using the application link below (google). In the form, the applicant is required to indicate:
- The estimated total travel costs
- The requested amount to be covered by SEMLA
Application URL: Poster submission link.
The awarded candidates will be notified by email. After the travel, the applicant should send the receipts to SEMLA to ask for reimbursement.
Abstract: Anomaly detection plays an important role in management of modern large-scale distributed systems. Logs, which record system runtime information, are widely used for anomaly detection. However, Unsupervised anomaly detection algorithms face challenges in addressing complex systems, which generate vast amounts of multivariate time series data. Timely anomaly detection is crucial for managing these systems effectively and minimizing downtime. This proactive approach minimizes system downtime and plays a vital role in incident management for large-scale systems. To address these challenges, a method called Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED) has been developed for detecting anomalies in CN PTC system logs. MSCRED leverages the power of multivariate time series data to perform anomaly detection and diagnosis. It creates multi-scale signature matrices that capture different levels of system statuses across various time steps. The method utilizes a convolutional encoder to capture inter-sensor correlations and a Convolutional Long-Short Term Memory (ConvLSTM) network with attention mechanisms to capture temporal patterns.
Abstract
Abstract: Language models such as RoBERTa, CodeBERT, and GraphCodeBERT have gotten much attention in the past three years for various Software Engineering tasks. Though these models are proven to have state-of-the-art performance for many SE tasks, such as code summarization, they often require to be fully fine-tuned for the downstream task. Is there a better way for fine-tuning these models that require training fewer parameters? Can we impose new information on the current models without pre-training them again? How do these models perform for different programming languages, especially low-resource ones with less training data available? How can we use the knowledge learned from other programming languages to improve the performance of low-resource languages? This talk will review a series of experiments and our contributions to answering these questions.
