Analogy as Nonparametric Bayesian Inference over Relational Systems

• URL: http://arxiv.org/abs/2006.04156v1
• Date: Sun, 7 Jun 2020 14:07:46 GMT
• Title: Analogy as Nonparametric Bayesian Inference over Relational Systems
• Authors: Ruairidh M. Battleday and Thomas L. Griffiths
• Abstract summary: We propose a Bayesian model that generalizes relational knowledge to novel environments by analogically weighting predictions from previously encountered relational structures. We show that this learner outperforms a naive, theory-based learner on relational data derived from random- and Wikipedia-based systems when experience with the environment is small.
• Score: 10.736626320566705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Much of human learning and inference can be framed within the computational problem of relational generalization. In this project, we propose a Bayesian model that generalizes relational knowledge to novel environments by analogically weighting predictions from previously encountered relational structures. First, we show that this learner outperforms a naive, theory-based learner on relational data derived from random- and Wikipedia-based systems when experience with the environment is small. Next, we show how our formalization of analogical similarity translates to the selection and weighting of analogies. Finally, we combine the analogy- and theory-based learners in a single nonparametric Bayesian model, and show that optimal relational generalization transitions from relying on analogies to building a theory of the novel system with increasing experience in it. Beyond predicting unobserved interactions better than either baseline, this formalization gives a computational-level perspective on the formation and abstraction of analogies themselves.

Related papers

• Toward Understanding In-context vs. In-weight Learning [50.24035812301655]
  We identify simplified distributional properties that give rise to the emergence and disappearance of in-context learning. We then extend the study to a full large language model, showing how fine-tuning on various collections of natural language prompts can elicit similar in-context and in-weight learning behaviour.
  arXiv  Detail & Related papers  (2024-10-30T14:09:00Z)
• ARN: Analogical Reasoning on Narratives [13.707344123755126]
  We develop a framework that operationalizes dominant theories of analogy, using narrative elements to create surface and system mappings. We show that while all LLMs can largely recognize near analogies, even the largest ones struggle with far analogies in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-10-02T08:58:29Z)
• Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
  We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data. Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
  arXiv  Detail & Related papers  (2023-07-12T16:28:21Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• Some recent advances in reasoning based on analogical proportions [9.861775841965386]
  Analogical proportions play a key role in the formalization of analogical inference. The paper first discusses how to improve analogical inference in terms of accuracy and in terms of computational cost.
  arXiv  Detail & Related papers  (2022-12-22T14:10:14Z)
• Investigating the Role of Centering Theory in the Context of Neural Coreference Resolution Systems [71.57556446474486]
  We investigate the connection between centering theory and modern coreference resolution systems. We show that high-quality neural coreference resolvers may not benefit much from explicitly modeling centering ideas. We formulate a version of CT that also models recency and show that it captures coreference information better compared to vanilla CT.
  arXiv  Detail & Related papers  (2022-10-26T12:55:26Z)
• Instance-Based Neural Dependency Parsing [56.63500180843504]
  We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set.
  arXiv  Detail & Related papers  (2021-09-28T05:30:52Z)
• MINIMALIST: Mutual INformatIon Maximization for Amortized Likelihood Inference from Sampled Trajectories [61.3299263929289]
  Simulation-based inference enables learning the parameters of a model even when its likelihood cannot be computed in practice. One class of methods uses data simulated with different parameters to infer an amortized estimator for the likelihood-to-evidence ratio. We show that this approach can be formulated in terms of mutual information between model parameters and simulated data.
  arXiv  Detail & Related papers  (2021-06-03T12:59:16Z)
• Probabilistic Analogical Mapping with Semantic Relation Networks [2.084078990567849]
  We present a new computational model of analogical mapping, based on semantic relation networks. We show that the model accounts for a broad range of phenomena involving analogical mapping by both adults and children.
  arXiv  Detail & Related papers  (2021-03-30T22:14:13Z)
• Building and Interpreting Deep Similarity Models [0.0]
  We propose to make similarities interpretable by augmenting them with an explanation in terms of input features. We develop BiLRP, a scalable and theoretically founded method to systematically decompose similarity scores on pairs of input features.
  arXiv  Detail & Related papers  (2020-03-11T17:46:55Z)
• Learning to See Analogies: A Connectionist Exploration [0.0]
  This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies.
  arXiv  Detail & Related papers  (2020-01-18T14:06:16Z)

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.