|
Alert: Accurate Learning for EneRgy and Timeliness in Software System
|
What is ALERT
Modern software systems increasingly rely on deep neural networks to perform a wide range of tasks like natural language translation and autonomous driving. The key to their success is that deep neural networks can well approximate these difficult tasks.
Unfortunately, the more accurate the approximation, the more resources it takes.
When deployed on mobile/IoT devices or autonomous vehicles,
those resource needs directly impact people as the time or energy/battery
required to produce an answer. Making things worse, misuses of deep neural networks could cause unnecessary degradation in accuracy and increase in resource
consumptions.
We will tackle these crucial problems by developing sound engineering methods to make disciplined tradeoffs between neural network accuracy and resource usage in software systems, and facilitate the right way of integrating deep neural networks into software systems.
People
Code Release
-
Reproduction kit for our ICSE 2021 paper on ML API misuses, including:
-
A suite with
hundreds of ML API misuses in open-source applications found by us.
-
Checkers to detect some of these misuses.
-
ML API Wrappers that prevent some of these misuses.
-
Reproduction kit for our ICSE 2022 paper on tesing software that uses ML API, including:
-
A testing tool and its IDE-plugin version developed by us.
-
A benchmark suite with 60+ applications and their evaluation results.
-
User study materials and results.
-
It is released as
VS Code Plugin!
Publications
-
ALERT: Accurate Learning for Energy and Timeliness
Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann, Michael Maire, and Shan Lu,
USENIX Annual Technical Conference
(ATC'20).
-
Orthogonalized SGD and Nested Architectures for Anytime Neural Networks
Chengcheng Wan, Henry Hoffmann, Shan Lu, Michael Maire,
Proceedings of the International Conference on Machine Learning 2020
(ICML'20).
-
Are Machine Learning Cloud APIs Used Correctly?
Chengcheng Wan, Shicheng Liu, Henry Hoffmann, Michael Maire, Shan Lu,
43rd International Conference on Software Engineering 2021
(ICSE'21).
(You can check the hundreds of ML API misuses found by us and our checkers
here.)
-
Budget RNNs: Multi-Capacity Neural Networks to Improve In-Sensor Inference Under Energy Budgets
Tejas Kannan, Henry Hoffmann
27th IEEE Real-Time and Embedded Technology and Applications Symposium
(RTAS 2021).
Won Outstanding Paper Award!
-
Growing Efficient Deep Networks by Structured Continuous Sparsification
Xin Yuan, Pedro Savarese, and Michael Maire
International Conference on Learning Representations (ICLR), 2021
(ICLR 2021).
-
Automated Testing of Software that Uses Machine Learning APIs
Chengcheng Wan, Shicheng Liu, Sophie Xie, Yifan Liu, Henry Hoffmann, Michael Maire, and Shan Lu,
44rd International Conference on Software Engineering 2022
(ICSE'22).
(You can check the testing tool developed by us
here.)
-
...
Funding
|
|
 |
|
