New in ML workshop at ICML 2022
- Feedback Form
- Registration Form
- Invited Speakers
- Call for papers
- Organization Team
- ICML 2022 Main Conference
Give us your feedback on the workshop!
Give my feedback
On-site attendance details for July 18, 2022
- Rooms 301-303, Baltimore Convention Center
- 8:45 - 9:00 - Welcome
- 9:00 - Workshop start
Online attendance details for July 18, 2022
- Workshop virtual site: link
- 9:00 - Workshop start
- Use the Rocket.Chat for questions (please remain polite and considerate of other attendees or speakers)
Interactive afternoon session - Writing effectively for ML
Here is a Handout with exercises presented by our speakers: handout
Registrations: Being registered for any component of the conference (tutorials, conference sessions, workshops, virtual only pass) allows you to attend any affinity events, including our workshop!
Is this your first time to a top conference? Have you ever wanted your own work recognized by this huge and active community? Do you encounter difficulties in polishing your ideas, experiments, paper writing, etc? Then, this session is exactly for you!
This year, we are hosting again the New in ML workshop, co-locating with ICML 2022. This workshop is intended for anyone who has not published a paper at a top conference yet (e.g. ICML, NeurIPS). We invited top researchers to review your work and share their experience with you. The best papers will get oral presentations and awards!
Our biggest goal is to help you publish papers at the next ICML conference, and generally provide you with the guidance you need to contribute to ML research fully and effectively!
Within quota limits, the authors of the best accepted papers may be receiving tickets to ICML 2022, to be attributed according to merit and need. In addition, we should be able to provide financial help for travel/accommodation/registration expanses and fees.
Though labeled as an affinity workshop, this workshop is open to everyone. It is a requirement to register for the ICML 2022 conference in order to attend the workshops, socials and anything connected to the ICML Conference platform, including this workshop. Being registered for any component of the conference (tutorials, conference sessions, workshops, virtual only pass) allows you to attend any affinity events, including our workshop. In addition, we would like to have an estimate of the number of attendees and their background. Please fill out the registration form intended for this purpose.
See more information about our invited speakers
Call for papers
See more information about our call for papers
This will be a one-day hybrid on site/online event in Baltimore, USA (Eastern Daylight Time/UTC−4).
You can find the workshop virtual site with the schedule on the following link.
Accepted extended abstracts
A Compact Transformer-based Classifier with Selected Hybrid Features from Different Patch Sequences for Image Classification, Luna Zhang
An Efficient Modern Baseline for FloodNet VQA, Aditya Kane, Sahil Khose
FedControl: When Control Theory Meets Federated Learning, Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis, David Naccache
Generating Synthetic Population, Bhavesh Neekhra, Kshitij Kapoor, Debayan Gupta
Light Weight Character and Shape Recognition for Autonomous Drones, Neetigya Poddar, Shruti Praveen Jain
Test-Time Adaptation with Principal Component Analysis, Thomas Cordier, Victor Bouvier, Gilles Hénaff, Céline Hudelot
Data Challenge opportunity: Cross-Domain MetaDL (NeurIPS 2022)
Here is a quick summary regarding a very interesting data challenge for NewInML folks. More details can be found in this extended abstract and on the challenge website.
The new Cross-Domain MetaDL challenge is part of the ChaLearn meta-learning series. It has a special league for New in ML participants (with prizes and certificates) and a detailed tutorial with no prerequisites (i.e., no previous meta-learning knowledge required). The competition is part of the NeurIPS’22 program, and the winners will be invited to co-author the analysis paper with the organizers to appear in PMLR. The focus is on “cross-domain” meta-learning, aiming at leveraging experience from previous tasks to solve new tasks efficiently. While our previous challenge addressed within-domain few-shot learning for N-way k-shot tasks (i.e., N class classification problems with k training examples), this challenge proposes “any-way” and “any-shot” tasks drawn from various domains (healthcare, ecology, biology, manufacturing, and others), chosen for their humanitarian and societal impact. Code submissions will be blind-tested on CodaLab, and the winners’ code will be open-sourced. Submissions are open between July 01 and August 31, 2022.
See more information about our organization team
Write us at: contactnewinml (at) gmail.com
Follow us on Twitter: @NewInML