An official website of the United States government
Drawing on parallels with biological immunity, this paper introduces a new use case for learning at the edge called survival-critical machine learning (SCML). Unlike federated learning, which assumes supervised learning with pre-labeled data, SCML involves semi-supervised learning in streaming settings where labels may need to be obtained at very low network bandwidth and extreme class imbalance. We show that the recently-developed workflow of Live Learning is a good fit for SCML. Starting from a weak bootstrap model, this workflow seamlessly pipelines semi-supervised learning, active learning, and transfer learning, with asynchronous bandwidth-sensitive data transmission for labeling. As improved models evolve at the edge through periodic re-training, the threat detection ability of the SCML system improves. This, in turn, improves the survivability of the host system.
more »
« less
Edge-Based Live Learning for Robot Survival
We introduce survival-critical machine learning (SCML), in which a robot encounters dynamically evolving threats that it recognizes via machine learning (ML), and then neutralizes. We model survivability in SCML, and show the value of the recently developed approach of Live Learning. This edge-based ML technique embodies an iterative human-in-the-loop workflow that concurrently enlarges the training set, trains the next model in a sequence of “best-so-far” models, and performs inferencing for both threat detection and pseudo-labeling. We present experimental results using datasets from the domains of drone surveillance, planetary exploration, and underwater sensing to quantify the effectiveness of Live Learning as a mechanism for SCML.
more »
« less
- Award ID(s):
- 2106862
- PAR ID:
- 10589000
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Transactions on Emerging Topics in Computing
- Volume:
- 13
- Issue:
- 1
- ISSN:
- 2376-4562
- Page Range / eLocation ID:
- 34 to 47
- Subject(s) / Keyword(s):
- Edge computing, machine learning, robotics
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)With the explosion in Big Data, it is often forgotten that much of the data nowadays is generated at the edge. Specifically, a major source of data is users' endpoint devices like phones, smart watches, etc., that are connected to the internet, also known as the Internet-of-Things (IoT). This "edge of data" faces several new challenges related to hardware-constraints, privacy-aware learning, and distributed learning (both training as well as inference). So what systems and machine learning algorithms can we use to generate or exploit data at the edge? Can network science help us solve machine learning (ML) problems? Can IoT-devices help people who live with some form of disability and many others benefit from health monitoring? In this tutorial, we introduce the network science and ML techniques relevant to edge computing, discuss systems for ML (e.g., model compression, quantization, HW/SW co-design, etc.) and ML for systems design (e.g., run-time resource optimization, power management for training and inference on edge devices), and illustrate their impact in addressing concrete IoT applications.more » « less
-
This paper describes how a system that performs Live Learning can be modified to use radar rather than visible light. The pipelined and iterative machine learning (ML) workflow of this system can operate at low network bandwidths for selective transmission of rare unlabeled events embedded in high-bandwidth real-time sensor data. While radar offers greater range and can overcome the severe signal attenuation experienced by visible light under conditions such as rain or fog, it poses a number of challenges for ML. This paper describes how these challenges can be overcome for Live Learning, and identifies some future directions for research.more » « less
-
Poole, Steve; Hernandez, Oscar; Baker, Matthew; Curtis, Tony (Ed.)SHMEM-ML is a domain specific library for distributed array computations and machine learning model training & inference. Like other projects at the intersection of machine learning and HPC (e.g. dask, Arkouda, Legate Numpy), SHMEM-ML aims to leverage the performance of the HPC software stack to accelerate machine learning workflows. However, it differs in a number of ways. First, SHMEM-ML targets the full machine learning workflow, not just model training. It supports a general purpose nd-array abstraction commonly used in Python machine learning applications, and efficiently distributes transformation and manipulation of this ndarray across the full system. Second, SHMEM-ML uses OpenSHMEM as its underlying communication layer, enabling high performance networking across hundreds or thousands of distributed processes. While most past work in high performance machine learning has leveraged HPC message passing communication models as a way to efficiently exchange model gradient updates, SHMEM-ML’s focus on the full machine learning lifecycle means that a more flexible and adaptable communication model is needed to support both fine and coarse grain communication. Third, SHMEM-ML works to interoperate with the broader Python machine learning software ecosystem. While some frameworks aim to rebuild that ecosystem from scratch on top of the HPC software stack, SHMEM-ML is built on top of Apache Arrow, an in-memory standard for data formatting and data exchange between libraries. This enables SHMEM-ML to share data with other libraries without creating copies of data. This paper describes the design, implementation, and evaluation of SHMEM-ML – demonstrating a general purpose system for data transformation and manipulation while achieving up to a 38× speedup in distributed training performance relative to the industry standard Horovod framework without a regression in model metrics.more » « less
-
null (Ed.)Online forums are an integral part of modern day courses, but motivating students to participate in educationally beneficial discussions can be challenging. Our proposed solution is to initialize (or “seed”) a new course forum with comments from past instances of the same course that are intended to trigger discussion that is beneficial to learning. In this work, we develop methods for selecting high-quality seeds and evaluate their impact over one course instance of a 186-student biology class. We designed a scale for measuring the “seeding suitability” score of a given thread (an opening comment and its ensuing discussion). We then constructed a supervised machine learning (ML) model for predicting the seeding suitability score of a given thread. This model was evaluated in two ways: first, by comparing its performance to the expert opinion of the course instructors on test/holdout data; and second, by embedding it in a live course, where it was actively used to facilitate seeding by the course instructors. For each reading assignment in the course, we presented a ranked list of seeding recommendations to the course instructors, who could review the list and filter out seeds with inconsistent or malformed content. We then ran a randomized controlled study, in which one group of students was shown seeds that were recommended by the ML model, and another group was shown seeds that were recommended by an alternative model that ranked seeds purely by the length of discussion that was generated in previous course instances. We found that the group of students that received posts from either seeding model generated more discussion than a control group in the course that did not get seeded posts. Furthermore, students who received seeds selected by the ML-based model showed higher levels of engagement, as well as greater learning gains, than those who received seeds ranked by length of discussion.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TETC.2024.3479082
