Measuring the Feasibility of Analogical Transfer using Complexity

• URL: http://arxiv.org/abs/2206.11753v1
• Date: Thu, 23 Jun 2022 14:52:16 GMT
• Title: Measuring the Feasibility of Analogical Transfer using Complexity
• Authors: Pierre-Alexandre Murena
• Abstract summary: We show how to quantify the transferability of a source case (A and B) to solve a target problem C. We illustrate these notions on morphological analogies and show its connections with machine learning.
• Score: 12.917492210639265
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Analogies are 4-ary relations of the form "A is to B as C is to D". While focus has been mostly on how to solve an analogy, i.e. how to find correct values of D given A, B and C, less attention has been drawn on whether solving such an analogy was actually feasible. In this paper, we propose a quantification of the transferability of a source case (A and B) to solve a target problem C. This quantification is based on a complexity minimization principle which has been demonstrated to be efficient for solving analogies. We illustrate these notions on morphological analogies and show its connections with machine learning, and in particular with Unsupervised Domain Adaptation.

Related papers

• Cluster-Aware Similarity Diffusion for Instance Retrieval [64.40171728912702]
  Diffusion-based re-ranking is a common method used for retrieving instances by performing similarity propagation in a nearest neighbor graph. We propose a novel Cluster-Aware Similarity (CAS) diffusion for instance retrieval.
  arXiv  Detail & Related papers  (2024-06-04T14:19:50Z)
• 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)
• ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base [51.777618249271725]
  ANALOGYKB is a million-scale analogy knowledge base derived from existing knowledge graphs (KGs) It identifies two types of analogies from the KGs: 1) analogies of the same relations, which can be directly extracted from the KGs, and 2) analogies of analogous relations, which are identified with a selection and filtering pipeline enabled by large language models (LLMs)
  arXiv  Detail & Related papers  (2023-05-10T09:03:01Z)
• Solving morphological analogies: from retrieval to generation [4.834203844100681]
  Analogical inference is a capability of human reasoning, and has been used to solve hard reasoning tasks. We propose a deep learning (DL) framework to address and tackle two key tasks in AR: analogy detection and solving. The framework is thoroughly tested on the Siganalogies dataset of morphological analogical proportions (APs) between words, and shown to outperform symbolic approaches in many languages.
  arXiv  Detail & Related papers  (2023-03-30T12:36:46Z)
• Galois theory for analogical classifiers [1.7132914341329848]
  Analogical proportions are 4-ary relations that read "A is to B as C is to D" Recent works have highlighted the fact that such relations can support a specific form of inference, called analogical inference.
  arXiv  Detail & Related papers  (2022-05-09T23:03:56Z)
• Quantifying and Understanding Adversarial Examples in Discrete Input Spaces [70.18815080530801]
  We formalize a notion of synonymous adversarial examples that applies in any discrete setting and describe a simple domain-agnostic algorithm to construct such examples. Our work is a step towards a domain-agnostic treatment of discrete adversarial examples analogous to that of continuous inputs.
  arXiv  Detail & Related papers  (2021-12-12T16:44:09Z)
• Tackling Morphological Analogies Using Deep Learning -- Extended Version [8.288496996031684]
  Analogical proportions are statements of the form "A is to B as C is to D" We propose an approach using deep learning to detect and solve morphological analogies. We demonstrate our model's competitive performance on analogy detection and resolution over multiple languages.
  arXiv  Detail & Related papers  (2021-11-09T13:45:23Z)
• A Neural Approach for Detecting Morphological Analogies [7.89271130004391]
  Analogical proportions are statements of the form "A is to B as C is to D" We propose a deep learning approach to detect morphological analogies.
  arXiv  Detail & Related papers  (2021-08-09T11:21:55Z)
• Disentangling Observed Causal Effects from Latent Confounders using Method of Moments [67.27068846108047]
  We provide guarantees on identifiability and learnability under mild assumptions. We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
  arXiv  Detail & Related papers  (2021-01-17T07:48:45Z)
• Few-shot Visual Reasoning with Meta-analogical Contrastive Learning [141.2562447971]
  We propose to solve a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning. We extract structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning. We validate our method on RAVEN dataset, on which it outperforms state-of-the-art method, with larger gains when the training data is scarce.
  arXiv  Detail & Related papers  (2020-07-23T14:00:34Z)
• Few-shot Domain Adaptation by Causal Mechanism Transfer [107.08605582020866]
  We study few-shot supervised domain adaptation (DA) for regression problems, where only a few labeled target domain data and many labeled source domain data are available. Many of the current DA methods base their transfer assumptions on either parametrized distribution shift or apparent distribution similarities. We propose mechanism transfer, a meta-distributional scenario in which a data generating mechanism is invariant among domains.
  arXiv  Detail & Related papers  (2020-02-10T02:16:53Z)

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.