paper-with-me

Papers

Transfer learning for semantic similarity measures based on symbolic regression

2023-07-02 · Journal of Intelligent & Fuzzy Systems 2023 7 · Jorge Martinez-Gil, Jose M. Chaves Gonzalez

Recently, transfer learning strategies have become ideal for reusing acquired knowledge through a training phase. The key idea is that reusing such knowledge brings advantages such as increased accuracy and considerable resource savings. In this work, we design a novel strategy for effective and efficient transfer learning in semantic similarity. Our approach is based on generating and transferring optimal models obtained through a symbolic regression process being able to stack evaluation scores from several fundamental techniques. After an exhaustive empirical study, the results lead to high accuracy in addition to significant savings in terms of training time consumed in most of the scenarios considered.

📄 PDF Abstract BibTeX

Code (1)

jorge-martinez-gil/transfer-learning-symreg

Tasks

regressionSemantic SimilaritySemantic Textual SimilaritySymbolic RegressionTransfer Learning

Similar Papers 제목 키워드 기반

Complexity Measures for Multi-objective Symbolic Regression

2021-09-01 · Michael Kommenda, Andreas Beham, Michael Affenzeller, Gabriel Kronberger

Multi-objective symbolic regression has the advantage that while the accuracy of the learned models is maximized, the complexity is automatically adapted and need not be specified a-priori. The result of the optimization…

regressionSymbolic Regression

SPINEX_ Symbolic Regression: Similarity-based Symbolic Regression with Explainable Neighbors Exploration

2024-11-05 · MZ Naser, Ahmed Z Naser

This article introduces a new symbolic regression algorithm based on the SPINEX (Similarity-based Predictions with Explainable Neighbors Exploration) family. This new algorithm (SPINEX_SymbolicRegression) adopts a simila…

BenchmarkingregressionSymbolic Regression

Deconfounded Representation Similarity for Comparison of Neural Networks

2022-01-31 · Tianyu Cui, Yogesh Kumar, Pekka Marttinen, Samuel Kaski

Similarity metrics such as representational similarity analysis (RSA) and centered kernel alignment (CKA) have been used to compare layer-wise representations between neural networks. However, these metrics are confounde…

Transfer Learning

Online Diversity Control in Symbolic Regression via a Fast Hash-based Tree Similarity Measure

2019-02-03 · Bogdan Burlacu, Michael Affenzeller, Gabriel Kronberger, Michael Kommenda

Diversity represents an important aspect of genetic programming, being directly correlated with search performance. When considered at the genotype level, diversity often requires expensive tree distance measures which h…

DiversityregressionSymbolic Regression

Transformer Semantic Genetic Programming for d-dimensional Symbolic Regression Problems

2025-11-12 · Philipp Anthes, Dominik Sobania, Franz Rothlauf arxiv

Transformer Semantic Genetic Programming (TSGP) is a semantic search approach that uses a pre-trained transformer model as a variation operator to generate offspring programs with high semantic similarity to a given pare…

Semantic Similarity