Feature Interactions on Steroids: On the Composition of ML Models

• URL: http://arxiv.org/abs/2105.06449v1
• Date: Thu, 13 May 2021 17:46:29 GMT
• Title: Feature Interactions on Steroids: On the Composition of ML Models
• Authors: Christian K\"astner, Eunsuk Kang, Sven Apel
• Abstract summary: Lack of specifications is a key difference between traditional software engineering and machine learning. We discuss how it drastically impacts how we think about divide-and-conquer approaches to system design.
• Score: 11.707367442890936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The lack of specifications is a key difference between traditional software engineering and machine learning. We discuss how it drastically impacts how we think about divide-and-conquer approaches to system design, and how it impacts reuse, testing and debugging activities. Traditionally, specifications provide a cornerstone for compositional reasoning and for the divide-and-conquer strategy of how we build large and complex systems from components, but those are hard to come by for machine-learned components. While the lack of specification seems like a fundamental new problem at first sight, in fact software engineers routinely deal with iffy specifications in practice: we face weak specifications, wrong specifications, and unanticipated interactions among components and their specifications. Machine learning may push us further, but the problems are not fundamentally new. Rethinking machine-learning model composition from the perspective of the feature interaction problem, we may even teach us a thing or two on how to move forward, including the importance of integration testing, of requirements engineering, and of design.

Related papers

• Machine Learning-Enabled Software and System Architecture Frameworks [48.87872564630711]
  The stakeholders with data science and Machine Learning related concerns, such as data scientists and data engineers, are yet to be included in existing architecture frameworks. We surveyed 61 subject matter experts from over 25 organizations in 10 countries.
  arXiv  Detail & Related papers  (2023-08-09T21:54:34Z)
• Learnware: Small Models Do Big [69.88234743773113]
  The prevailing big model paradigm, which has achieved impressive results in natural language processing and computer vision applications, has not yet addressed those issues, whereas becoming a serious source of carbon emissions. This article offers an overview of the learnware paradigm, which attempts to enable users not need to build machine learning models from scratch, with the hope of reusing small models to do things even beyond their original purposes.
  arXiv  Detail & Related papers  (2022-10-07T15:55:52Z)
• Ising machines as hardware solvers of combinatorial optimization problems [1.8732539895890135]
  Ising machines are hardware solvers which aim to find the absolute or approximate ground states of the Ising model. A scalable Ising machine that outperforms existing standard digital computers could have a huge impact for practical applications.
  arXiv  Detail & Related papers  (2022-04-01T08:24:06Z)
• Symmetry Group Equivariant Architectures for Physics [52.784926970374556]
  In the domain of machine learning, an awareness of symmetries has driven impressive performance breakthroughs. We argue that both the physics community and the broader machine learning community have much to understand.
  arXiv  Detail & Related papers  (2022-03-11T18:27:04Z)
• Towards Machine Learning for Placement and Routing in Chip Design: a Methodological Overview [72.79089075263985]
  Placement and routing are two indispensable and challenging (NP-hard) tasks in modern chip design flows. Machine learning has shown promising prospects by its data-driven nature, which can be of less reliance on knowledge and priors.
  arXiv  Detail & Related papers  (2022-02-28T06:28:44Z)
• Panoramic Learning with A Standardized Machine Learning Formalism [116.34627789412102]
  This paper presents a standardized equation of the learning objective, that offers a unifying understanding of diverse ML algorithms. It also provides guidance for mechanic design of new ML solutions, and serves as a promising vehicle towards panoramic learning with all experiences.
  arXiv  Detail & Related papers  (2021-08-17T17:44:38Z)
• Federated Learning: A Signal Processing Perspective [144.63726413692876]
  Federated learning is an emerging machine learning paradigm for training models across multiple edge devices holding local datasets, without explicitly exchanging the data. This article provides a unified systematic framework for federated learning in a manner that encapsulates and highlights the main challenges that are natural to treat using signal processing tools.
  arXiv  Detail & Related papers  (2021-03-31T15:14:39Z)
• Fanoos: Multi-Resolution, Multi-Strength, Interactive Explanations for Learned Systems [0.0]
  Fanoos is a framework for combining formal verification techniques, search, and user interaction to explore explanations at the desired level of granularity and fidelity. We demonstrate the ability of Fanoos to produce and adjust the abstractness of explanations in response to user requests on a learned controller for an inverted double pendulum and on a learned CPU usage model.
  arXiv  Detail & Related papers  (2020-06-22T17:35:53Z)
• Integrating Machine Learning with Physics-Based Modeling [17.392391163553334]
  This article focuses on one particular issue of broad interest: How can we integrate machine learning with physics-based modeling? We discuss the two most important issues for developing machine learning-based physical models: Imposing physical constraints and obtaining optimal datasets. We end with a general discussion on where this integration will lead us, and where the new frontier will be after machine learning is successfully integrated into scientific modeling.
  arXiv  Detail & Related papers  (2020-06-04T02:35:10Z)
• Understanding What Software Engineers Are Working on -- The Work-Item Prediction Challenge [0.0]
  Understanding what a software engineer (a developer, an incident responder, a production engineer, etc.) is working on is a challenging problem. In this paper, we explain the corresponding 'work-item prediction challenge' on the grounds of representative scenarios.
  arXiv  Detail & Related papers  (2020-04-13T19:59:36Z)
• Teaching Software Engineering for AI-Enabled Systems [7.01053472751897]
  This course teaches software-engineering skills to students with a background in machine learning. We describe the course and our infrastructure and share experience and all material from teaching the course for the first time.
  arXiv  Detail & Related papers  (2020-01-18T15:24:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.