DataLab

The course

Work in groups of three on collaborative filtering, generative models and adversarial robustness. For each project, implement an approach, compare it against baselines, and explain what your experiments teach you in a short talk and a report.

Registration & groups — action required

Your TODO

• Complete your name and email in the registration sheet, next to your GitHub ID.
• Check the A1 final presentation order · 22 October. Be ready from the start of the session.
• A2: choose new teammates. No pair of students from an A1 group may work together again in A2. Check the group rule before joining a team.

Assessment & submissions

• One presentation per group, per project. A1 and A2: preliminary or final. A3: final only, for everyone. A1/A2 provisional allocation: 19 groups in preliminary and 18 in final. Each presentation lasts 5 minutes. An alarm rings at 5 minutes: finish your talk when it rings. A further 2 minutes per group are reserved for questions and transition. A3 timing will be announced separately.
• One final report per project: one group cover page + at most five pages of content. Optional appendices are not read.
• Code itself is not graded. Your report and talk must explain your methods, experimental protocol, results and limitations. The required code interface must work for automated tests.
• AI is allowed. You must understand, verify and be able to defend everything you submit. Interpret results rather than simply describing them. Expectations increase from A1 to A3.

Files and deadlines

Push slides.pdf and report.pdf to the root of your group repository. Slides are due at 23:59 the day before your presentation; the final report is due at 23:59 the day before the final session, for all groups. Code can be updated until 05:00 on the final-session day. All times are Paris time.

Late submissions will not be accepted. Missing or incorrectly named files will be penalised. Check your pushed PDFs on GitHub before the deadline.

Daily testing

Your repository is pulled and tested each morning around 05:00. Results appear after the runs finish. The DataLab results links will be announced below. These tests provide feedback for your experiments.

Schedule

A1: 40 active groups · allocation updated on 15 October. Each presentation lasts 5 minutes, with an alarm at 5 minutes, followed by 2 minutes for questions and transition. Preliminary: 22 groups · 154 minutes (2 h 34). Final: 18 groups · 126 minutes (2 h 06). Group lists and presentation dates are below.

Sessions generally last three hours. The A1 preliminary session on 15 October uses an extended presentation window of 2 h 34. On 22 October, the last 40 minutes are reserved for the introduction to A2 and precision–recall. A2 group allocation remains provisional.

Collaborative filtering

Predict missing ratings using matrix factorisation and alternative recommendation methods. Compare approaches and study hyperparameters, regularisation and computational cost.

The three volunteer groups are included in the preliminary session. The remaining preliminary groups were drawn at random. These alphabetical lists indicate your presentation date, not your speaking order. The preliminary running order remains available for reference. The final presentation order is now available above. Please be ready from the start of your session.

All groups: upload report.pdf by 21 October at 23:59, including groups presenting on 15 October. Code remains modifiable until 22 October at 05:00.

Check the latest assignments on the Find your A1 group page. Contact Alexandre if your group is missing or incorrect.

Generative models

Study generation quality and diversity through precision and recall. Design controlled comparisons and explain the trade-offs you observe.

Train the MNIST GAN with the provided generator architecture kept fixed. The platform measures FID, precision and recall and displays generated-image galleries.

Request a preliminary presentation

Email Alexandre with your group name, members and repository link by the end of Thursday 22 October if you would like to present in preliminary. On Saturday 31 October, the remaining presentation dates will be assigned randomly and the remaining students will be assigned to groups. The confirmed allocation will be published here.

Adversarial robustness

Understand adversarial attacks and assess the robustness of classifiers. Support your conclusions with careful experiments and critical analysis.

Slides, Classroom 50 invitation and testing platform: coming soon.

Final presentations · 3 December

All groups present in the final session. There is no preliminary session for A3.

With 37 groups, five-minute talks plus two minutes for questions and transition would require 4 h 19. The A3 presentation format will be announced separately.

Group list, order and speaking times: to be announced.

MesoNET & Slurm

Prepare your account before the practical introduction on 8 October.

1. Request an account through the MesoNET account procedure, using eduGAIN and your institutional account. Mention IASD.
2. Validate your email, wait for approval, then complete your MesoNET profile before emailing Alexandre.
3. Email Alexandre with your name, MesoNET username and registration email to request access to the IASD project.
4. Prepare your SSH public key. The course introduction contains the SSH setup instructions.

The example includes Python code, configurations, Slurm scripts, the interactive analysis notebook, recorded results and the two trained best.pt models. Start with README.md. You can explore the prepared results without retraining. Download CIFAR-10 separately to train; the larger resume checkpoints and environments are not included.