Time in Eastern Time (US & Canada).
June 12, 2024
| 8:30 – 9:00 | Breakfast (—) |
| 9:00 – 9:15 | SEMLA 2022 Opening Session Opening by Prof. Foutse Khomh |
| Session I: Privacy and Security of AI/FMs – Moderator: TBA | |
| 9:15-10:45 | Negar Rostamzadeh (Google, MILA, Canada): Beyond the ML Model: From Plane Crash to Algorithmic Harms. Xi He (University of Waterloo, Vector Institute, Canada): TBA. Jie Zhang (King’s College London, UK): TBA |
| 10:45-11:00 | Coffee break |
| 11:00-11:30 | Elnaz Kanani (Deloitte Canada): Enhancing public services: leveraging artificial intelligence for government efficiency |
| 11:30-12:30 | Panel Discussion: TBA – Moderator: TBA Negar Rostamzadeh (Google, MILA, Canada) Xi He (University of Waterloo, Vector Institute, Canada) Elnaz Kanani (Deloitte Canada) Jie Zhang (King’s College London, UK) |
| 12:30-14:00 | Lunch break |
| Session II: Engineering of Trustworthy FMs – Moderator: TBA | |
| 14:00-15:30 | Ahmed E. Hassan (Queen’s University, Canada): TBA Alexandra Olteanu (Microsoft Research, Canada) |
| 15:30-16:00 | Coffee break |
| 16:00-16:30 | Karime Maamari (Distyl AI, USA): Tackling NL-to-SQL’s End-to-End Cross-Cutting Issues: Strategic Preprocessing and Optimization |
| 16:30-17:30 | Panel Discussion: TBA – Moderator: TBA Ahmed E. Hassan (Queen’s University, Canada) Alexandra Olteanu (Microsoft Research, Canada) Karime Maamari (Distyl AI, USA) |
| 17:30-19:00 | Reception & Poster session — Poster chair: Mohammad Hamdaqa & Bentley Oakes |
June 13, 2024
| 8:30 – 9:00 | Breakfast (—) |
| Session III: AI/FMs for Software Engineering – Moderator: TBA | |
| 9:00-10:30 | David Lo (Singapore Management University, Singapore) : Efficacy, Efficiency, and Security of Code LLMs: Promises and Perils Prem Devanbu (UC Davis, USA): Bimodality in Software |
| 10:45-11:00 | Coffee break |
| 11:00-11:30 | Anh Nguyen-Duc (South Eastern Norway and Norwegian University of Science and Technology): On the impact of GenAI in software development – the state of art and future prospects |
| 11:30-12:30 | Panel Discussion: TBA – Moderator: TBA David Lo (Singapore Management University, Singapore) : TBA Prem Devanbu (UC Davis, USA): TBA Anh Nguyen-Duc (South Eastern Norway and Norwegian University of Science and Technology) |
| 12:30-14:00 | Lunch break |
| Session IV: Fairness and Transparency of AI/FMs – Moderator: TBA | |
| 14:00-15:30 | Denys Poshyvanyk (William & Mary, USA): Towards an Interpretable Science of Deep Learning for Software Engineering: A Causal Inference View Lingming Zhang (University of Illinois at Urbana-Champaign, USA): LLM4Code (magicoder and starcoder2) and their applications in software quality assurance |
| 15:30-16:00 | Coffee break |
| 16:00-16:30. | Golnoosh Farnadi (McGill University, Canada) |
| 16:30-17:30 | Panel Discussion: TBA – Moderator: TBA Denys Poshyvanyk (William & Mary, USA): TBA Golnoosh Farnadi (McGill University, Canada) Lingming Zhang (University of Illinois at Urbana-Champaign, USA) |
| 17:30-18:00 | Closing remarks |
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.
