Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design

• URL: http://arxiv.org/abs/2303.02884v1
• Date: Mon, 6 Mar 2023 04:31:36 GMT
• Title: Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design
• Authors: Michelle S. Lam, Zixian Ma, Anne Li, Izequiel Freitas, Dakuo Wang, James A. Landay, Michael S. Bernstein
• Abstract summary: Machine learning practitioners end up on low-level technical details like model architectures and performance metrics. We introduce model sketching: a technical framework for iteratively and rapidly functional approximations of model decision-making.
• Score: 29.775425128670573
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning practitioners often end up tunneling on low-level technical details like model architectures and performance metrics. Could early model development instead focus on high-level questions of which factors a model ought to pay attention to? Inspired by the practice of sketching in design, which distills ideas to their minimal representation, we introduce model sketching: a technical framework for iteratively and rapidly authoring functional approximations of a machine learning model's decision-making logic. Model sketching refocuses practitioner attention on composing high-level, human-understandable concepts that the model is expected to reason over (e.g., profanity, racism, or sarcasm in a content moderation task) using zero-shot concept instantiation. In an evaluation with 17 ML practitioners, model sketching reframed thinking from implementation to higher-level exploration, prompted iteration on a broader range of model designs, and helped identify gaps in the problem formulation$\unicode{x2014}$all in a fraction of the time ordinarily required to build a model.

Related papers

• From Black-box to Causal-box: Towards Building More Interpretable Models [57.23201263629627]
  We introduce the notion of causal interpretability, which formalizes when counterfactual queries can be evaluated from a specific class of models.<n>We derive a complete graphical criterion that determines whether a given model architecture supports a given counterfactual query.
  arXiv  Detail & Related papers  (2025-10-24T20:03:18Z)
• Freehand Sketch Generation from Mechanical Components [16.761960706420066]
  MSFormer is first time to produce humanoid freehand sketches tailored for mechanical components. First stage employs Open CASCADE technology to obtain multi-view contour sketches from mechanical components. Second stage translates contour sketches into freehand sketches by a transformer-based generator.
  arXiv  Detail & Related papers  (2024-08-12T07:44:19Z)
• Mining Frequent Structures in Conceptual Models [2.841785306638839]
  We propose a general approach to the problem of discovering frequent structures in conceptual modeling languages. We use the combination of a frequent subgraph mining algorithm and graph manipulation techniques. The primary objective is to offer a support facility for language engineers.
  arXiv  Detail & Related papers  (2024-06-11T10:24:02Z)
• Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use [14.2527771630478]
  We propose a new framework that alleviates manual effort by replacing human labeling with natural language interactions. Our framework eliminates the need for crowd-sourced annotations. Our trained models outperform traditional Agile Modeling as well as state-of-the-art zero-shot classification models.
  arXiv  Detail & Related papers  (2024-03-05T03:34:11Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse [59.500060790983994]
  This paper introduces ZhiJian, a comprehensive and user-friendly toolbox for model reuse, utilizing the PyTorch backend. ZhiJian presents a novel paradigm that unifies diverse perspectives on model reuse, encompassing target architecture construction with PTM, tuning target model with PTM, and PTM-based inference.
  arXiv  Detail & Related papers  (2023-08-17T19:12:13Z)
• fAIlureNotes: Supporting Designers in Understanding the Limits of AI Models for Computer Vision Tasks [32.53515595703429]
  fAIlureNotes is a designer-centered failure exploration and analysis tool. It supports designers in evaluating models and identifying failures across diverse user groups and scenarios.
  arXiv  Detail & Related papers  (2023-02-22T23:41:36Z)
• Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning [56.50123642237106]
  Common practice in model-based reinforcement learning is to learn models that model every aspect of the agent's environment. We argue that such models are not particularly well-suited for performing scalable and robust planning in lifelong reinforcement learning scenarios. We propose new kinds of models that only model the relevant aspects of the environment, which we call "minimal value-minimal partial models"
  arXiv  Detail & Related papers  (2023-01-24T16:40:01Z)
• Prototype-guided Cross-task Knowledge Distillation for Large-scale Models [103.04711721343278]
  Cross-task knowledge distillation helps to train a small student model to obtain a competitive performance. We propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios.
  arXiv  Detail & Related papers  (2022-12-26T15:00:42Z)
• Foundation models in brief: A historical, socio-technical focus [2.5991265608180396]
  Foundation models can be disruptive for future AI development by scaling up deep learning. Models achieve state-of-the-art performance on a variety of tasks in domains such as natural language processing and computer vision.
  arXiv  Detail & Related papers  (2022-12-17T22:11:33Z)
• Inter-model Interpretability: Self-supervised Models as a Case Study [0.2578242050187029]
  We build on a recent interpretability technique called Dissect to introduce textitinter-model interpretability We project 13 top-performing self-supervised models into a Learned Concepts Embedding space that reveals proximities among models from the perspective of learned concepts. The experiment allowed us to categorize the models into three categories and revealed for the first time the type of visual concepts different tasks requires.
  arXiv  Detail & Related papers  (2022-07-24T22:50:18Z)
• What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization? [50.84738303888189]
  We present a large-scale evaluation of modeling choices and their impact on zero-shot generalization. We train models with over 5 billion parameters for more than 170 billion tokens. We find that pretrained causal decoder models can be efficiently adapted into non-causal decoder models.
  arXiv  Detail & Related papers  (2022-04-12T14:19:49Z)
• Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks [53.09649785009528]
  In this paper, we explore a paradigm that does not require training to obtain new models. Similar to the birth of CNN inspired by receptive fields in the biological visual system, we propose Model Disassembling and Assembling. For model assembling, we present the alignment padding strategy and parameter scaling strategy to construct a new model tailored for a specific task.
  arXiv  Detail & Related papers  (2022-03-25T05:27:28Z)

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.