From Theory to Behaviour: Towards a General Model of Engagement

• URL: http://arxiv.org/abs/2004.12644v1
• Date: Mon, 27 Apr 2020 08:44:30 GMT
• Title: From Theory to Behaviour: Towards a General Model of Engagement
• Authors: Valerio Bonometti, Charles Ringer, Mathieu Ruiz, Alex Wade, Anders Drachen
• Abstract summary: We operationalize engagement mechanistically by linking it directly to human behaviour. We show that the construct of engagement can be used for shaping and interpreting data-driven methods.
• Score: 3.9198548406564604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Engagement is a fuzzy concept. In the present work we operationalize engagement mechanistically by linking it directly to human behaviour and show that the construct of engagement can be used for shaping and interpreting data-driven methods. First we outline a formal framework for engagement modelling. Second we expanded on our previous work on theory-inspired data-driven approaches to better model the engagement process by proposing a new modelling technique, the Melchoir Model. Third, we illustrate how, through model comparison and inspection, we can link machine-learned models and underlying theoretical frameworks. Finally we discuss our results in light of a theory-driven hypothesis and highlight potential application of our work in industry.

Related papers

• Exploring Model Kinship for Merging Large Language Models [52.01652098827454]
  We introduce model kinship, the degree of similarity or relatedness between Large Language Models. We find that there is a certain relationship between model kinship and the performance gains after model merging. We propose a new model merging strategy: Top-k Greedy Merging with Model Kinship, which can yield better performance on benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-16T14:29:29Z)
• Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities [89.40778301238642]
  Model merging is an efficient empowerment technique in the machine learning community. There is a significant gap in the literature regarding a systematic and thorough review of these techniques.
  arXiv  Detail & Related papers  (2024-08-14T16:58:48Z)
• Aligning Models with Their Realization through Model-based Systems Engineering [0.0]
  We propose a method for aligning models with their realization through the application of model-based systems engineering. Our approach facilitates a more seamless integration of models and implementation, fostering enhanced Business-IT alignment.
  arXiv  Detail & Related papers  (2024-06-18T06:50:36Z)
• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models. We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model. We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models [51.43538150982291]
  We study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we show that concepts can be provably recovered from diverse data.
  arXiv  Detail & Related papers  (2024-02-14T15:23:59Z)
• Has Your Pretrained Model Improved? A Multi-head Posterior Based Approach [25.927323251675386]
  We leverage the meta-features associated with each entity as a source of worldly knowledge and employ entity representations from the models. We propose using the consistency between these representations and the meta-features as a metric for evaluating pre-trained models. Our method's effectiveness is demonstrated across various domains, including models with relational datasets, large language models and image models.
  arXiv  Detail & Related papers  (2024-01-02T17:08:26Z)
• Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals [16.67633872254042]
  Counterfactual explanations offer an intuitive and straightforward way to explain black-box models. Existing work has primarily relied on surrogate models to learn how the input data is distributed. We propose a novel algorithmic framework for generating Energy-Constrained Conformal Counterfactuals that are only as plausible as the model permits.
  arXiv  Detail & Related papers  (2023-12-17T08:24:44Z)
• 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)
• An Ample Approach to Data and Modeling [1.0152838128195467]
  We describe a framework for modeling how models can be built that integrates concepts and methods from a wide range of fields. The reference M* meta model framework is presented, which relies critically in associating whole datasets and respective models in terms of a strict equivalence relation. Several considerations about how the developed framework can provide insights about data clustering, complexity, collaborative research, deep learning, and creativity are then presented.
  arXiv  Detail & Related papers  (2021-10-05T01:26:09Z)
• A Theoretical Approach for a Novel Model to Realizing Empathy [0.0]
  This paper introduces a theoretical concept as a proposed model that visualizes the process of realizing empathy. The intended purpose of this proposed model, is to create an initial blueprint that may be applicable to a range of disciplines.
  arXiv  Detail & Related papers  (2020-09-03T17:21:49Z)
• Control as Hybrid Inference [62.997667081978825]
  We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
  arXiv  Detail & Related papers  (2020-07-11T19:44:09Z)

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.