Workshop
Challenges in Deploying and Monitoring Machine Learning Systems
Alessandra Tosi · Andrei Paleyes · Christian Cabrera · Fariba Yousefi · S Roberts
Virtual
Fri 9 Dec, 1 a.m. PST
The goal of this event is to bring together people from different communities with the common interest in the Deployment of Machine Learning Systems.
With the dramatic rise of companies dedicated to providing Machine Learning software-as-a-service tools, Machine Learning has become a tool for solving real world problems that is increasingly more accessible in many industrial and social sectors. With the growth in number of deployments, also grows the number of known challenges and hurdles that practitioners face along the deployment process to ensure the continual delivery of good performance from deployed Machine Learning systems. Such challenges can lie in adoption of ML algorithms to concrete use cases, discovery and quality of data, maintenance of production ML systems, as well as ethics.
Schedule
Fri 1:00 a.m. - 1:05 a.m.
|
Opening Remarks
(
Introduction
)
>
SlidesLive Video |
Alessandra Tosi · Andrei Paleyes 🔗 |
Fri 1:05 a.m. - 1:25 a.m.
|
Lessons from the deployment of data science during the COVID-19 response in Africa.
(
Invited talk
)
>
SlidesLive Video |
Morine Amutorine 🔗 |
Fri 1:25 a.m. - 1:40 a.m.
|
Lessons from the deployment of data science during the COVID-19 response in Africa.
(
Q/A for Invited talk
)
>
|
Morine Amutorine · Alessandra Tosi 🔗 |
Fri 1:40 a.m. - 2:20 a.m.
|
Taking federated analytics from theory to practice
(
Invited talk
)
>
SlidesLive Video |
Graham Cormode 🔗 |
Fri 2:20 a.m. - 2:35 a.m.
|
Taking federated analytics from theory to practice
(
Q/A for Invited talk
)
>
|
Graham Cormode · Alessandra Tosi 🔗 |
Fri 2:35 a.m. - 2:45 a.m.
|
Break
|
🔗 |
Fri 2:55 a.m. - 3:08 a.m.
|
MLOps: Open Challenges from Hardware and Software Perspective in TinyML Devices
(
Poster
)
>
SlidesLive Video |
Seong Oun Hwang 🔗 |
Fri 3:08 a.m. - 3:19 a.m.
|
Deploying Imitation Learning using VR Hand Tracking in Robot Manipulation Tasks
(
Poster
)
>
SlidesLive Video |
Jinchul Choi · Chanwon Park · JUN HEE PARK 🔗 |
Fri 3:19 a.m. - 3:31 a.m.
|
MLOps for Compositional AI
(
Poster
)
>
SlidesLive Video |
Debmalya Biswas 🔗 |
Fri 3:31 a.m. - 3:44 a.m.
|
Tree DNN: A Deep Container Network
(
Poster
)
>
SlidesLive Video |
Brijraj Singh · Swati Gupta · Mayukh Das · Praveen Doreswamy Naidu · Sharan Allur 🔗 |
Fri 3:50 a.m. - 4:30 a.m.
|
A Case for Rejection in Low Resource ML Deployment
(
Poster
)
>
|
Jerome White · Jigar Doshi · Pulkit Madaan · Nikhil Shenoy · Apoorv Agnihotri · Makkunda Sharma 🔗 |
Fri 3:50 a.m. - 4:30 a.m.
|
Post-Training Neural Network Compression With Variational Bayesian Quantization
(
Poster
)
>
|
Zipei Tan · Robert Bamler 🔗 |
Fri 3:50 a.m. - 4:30 a.m.
|
Continual learning on deployment pipelines for Machine Learning Systems
(
Poster
)
>
|
Li Qiang · Chongyu Zhang 🔗 |
Fri 3:50 a.m. - 4:30 a.m.
|
Desiderata for next generation of ML model serving
(
Poster
)
>
|
Sherif Akoush · Andrei Paleyes · Arnaud Van Looveren · Clive Cox 🔗 |
Fri 4:30 a.m. - 5:48 a.m.
|
Break
|
🔗 |
Fri 5:48 a.m. - 5:50 a.m.
|
Introduction to the second session
(
Introduction
)
>
|
Christian Cabrera 🔗 |
Fri 5:50 a.m. - 6:25 a.m.
|
Reinforcement learning in large-scale heterogeneous dynamic systems
(
Invited talk
)
>
SlidesLive Video |
Ivana Dusparic 🔗 |
Fri 6:25 a.m. - 6:37 a.m.
|
Reinforcement learning in large-scale heterogeneous dynamic systems
(
Q/A for Invited talk
)
>
|
Ivana Dusparic 🔗 |
Fri 6:37 a.m. - 6:44 a.m.
|
Gumbel-Softmax Selective Networks
(
Contributed talk
)
>
SlidesLive Video |
Mahmoud Salem · · Fred Tung · Gabriel Oliveira 🔗 |
Fri 6:44 a.m. - 6:53 a.m.
|
A Preliminary Study of MLOps Practices in GitHub
(
Poster
)
>
SlidesLive Video |
Fabio Calefato · Filippo Lanubile · Luigi Quaranta 🔗 |
Fri 6:53 a.m. - 6:55 a.m.
|
Introduction to the speaker
(
Introduction
)
>
|
Andrei Paleyes 🔗 |
Fri 6:55 a.m. - 7:35 a.m.
|
Security in production machine learning systems
(
Invited talk
)
>
SlidesLive Video |
Alejandro Saucedo 🔗 |
Fri 7:35 a.m. - 7:50 a.m.
|
Security in production machine learning systems
(
Q/A for Invited talk
)
>
|
Alejandro Saucedo 🔗 |
Fri 7:50 a.m. - 8:00 a.m.
|
Break
|
🔗 |
Fri 8:00 a.m. - 9:00 a.m.
|
Panel on Open Problems in Machine Learning Systems
(
Panel discussion
)
>
SlidesLive Video |
Ivana Dusparic · Stephen J Roberts · Morine Amutorine · Jerome White · Murtuza Shergadwala 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
A Human-Centric Take on Model Monitoring
(
Poster
)
>
SlidesLive Video |
Murtuza Shergadwala · Himabindu Lakkaraju · Krishnaram Kenthapadi 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
AutoSlicer: Scalable Automated Data Slicing for ML Model Analysis
(
Poster
)
>
SlidesLive Video |
Zifan Liu · Evan Rosen · Paul Suganthan 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
Gumbel-Softmax Selective Networks
(
Poster
)
>
|
Mahmoud Salem · · Fred Tung · Gabriel Oliveira 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
(
Poster
)
>
SlidesLive Video |
20 presentersVashist Avadhanula · Omar Abdul Baki · Hamsa Bastani · Osbert Bastani · Caner Gocmen · Daniel Haimovich · Darren Hwang · Dmytro Karamshuk · Thomas Leeper · Jiayuan Ma · Gregory macnamara · Jake Mullet · Christopher Palow · Sung Park · Varun S Rajagopal · Kevin Schaeffer · Parikshit Shah · Deeksha Sinha · Nicolas Stier-Moses · Ben Xu |
Fri 9:00 a.m. - 9:30 a.m.
|
Just Following AI Orders: When Unbiased People Are Influenced By Biased AI
(
Poster
)
>
SlidesLive Video |
Hammaad Adam · Aparna Balagopalan · Emily Alsentzer · Fotini Christia · Marzyeh Ghassemi 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
Characterizing Anomalies with Explainable Classifiers
(
Poster
)
>
SlidesLive Video |
Naveen Durvasula · Valentine d Hauteville · Keegan Hines · John Dickerson 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
SEIFER: Scalable Edge Inference for Deep Neural Networks
(
Poster
)
>
SlidesLive Video |
Arjun Parthasarathy · Bhaskar Krishnamachari 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters
(
Poster
)
>
|
Arnav Chakravarthy · Nina Narodytska · Asmitha Rathis · Marius Vilcu · Mahmood Sharif · Gagandeep Singh 🔗 |
Fri 9:30 a.m. - 10:00 a.m.
|
Practical differential privacy
(
Invited talk
)
>
SlidesLive Video |
Yu-Xiang Wang 🔗 |
Fri 10:00 a.m. - 10:15 a.m.
|
Practical differential privacy
(
Q/A for Invited talk
)
>
|
Yu-Xiang Wang · Fariba Yousefi 🔗 |
Fri 10:15 a.m. - 11:15 a.m.
|
Panel on Privacy and Security in Machine Learning Systems
(
Panel discussion
)
>
SlidesLive Video |
Graham Cormode · Borja Balle · Yu-Xiang Wang · Alejandro Saucedo · Neil Lawrence 🔗 |
-
|
AutoSlicer: Scalable Automated Data Slicing for ML Model Analysis
(
Contributed talk
)
>
|
Zifan Liu · Evan Rosen · Paul Suganthan 🔗 |
-
|
Deploying Imitation Learning using VR Hand Tracking in Robot Manipulation Tasks
(
Contributed talk
)
>
|
Jinchul Choi · Chanwon Park · JUN HEE PARK 🔗 |
-
|
Tree DNN: A Deep Container Network
(
Contributed talk
)
>
|
Brijraj Singh · Swati Gupta · Mayukh Das · Praveen Doreswamy Naidu · Sharan Allur 🔗 |
-
|
Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
(
Contributed talk
)
>
|
20 presentersVashist Avadhanula · Omar Abdul Baki · Hamsa Bastani · Osbert Bastani · Caner Gocmen · Daniel Haimovich · Darren Hwang · Dmytro Karamshuk · Thomas Leeper · Jiayuan Ma · Gregory macnamara · Jake Mullet · Christopher Palow · Sung Park · Varun S Rajagopal · Kevin Schaeffer · Parikshit Shah · Deeksha Sinha · Nicolas Stier-Moses · Ben Xu |
-
|
Post-Training Neural Network Compression With Variational Bayesian Quantization
(
Contributed talk
)
>
|
Zipei Tan · Robert Bamler 🔗 |
-
|
MLOps for Compositional AI
(
Contributed talk
)
>
|
Debmalya Biswas 🔗 |
-
|
A Preliminary Study of MLOps Practices in GitHub
(
Poster
)
>
|
🔗 |