The committee will consider and evaluate any poster presentation relevant to SEMLA’s main topic, software engineering, and ML/AI. The poster session is a venue to present research results or highlight research practices and preliminary results.
SEMLA 2023 is offering a travel grant sponsored by Airudi Inc. to assist students with travel costs associated with attending the event. For more information, please check our travel support page.
Submission requirements
Please consult the following form (submission link) to submit your poster. You will be asked to include the following information:
1) Poster title
2) Poster abstract (up to 200 words)
3) Author name(s) (with the presenter(s) highlighted) and affiliation
Deadlines
Submission deadline: May 15, 2023
Acceptance notifications: May 17, 2023
Evaluation criteria
Proposals are evaluated based on the quality of the abstract and the degree of the work focus and relevance to SEMLA’s 2023 theme.
Format and requirements
The poster size should be no bigger than 24 x 36 inches. There is no required template.
Please contact Prof. Zorhreh Sharafi (zohreh.sharafi@polymtl.ca) for any questions.
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.
