Behavior of Analogical Inference w.r.t. Boolean Functions

Miguel Couceiro 1 Nicolas Hug 2 Henri Prade 2 Gilles Richard 2
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : It has been observed that a particular form of ana-logical inference, based on analogical proportions, yields competitive results in classification tasks. Using the algebraic normal form of Boolean functions , it has been shown that analogical prediction is always exact iff the labeling function is affine. We point out that affine functions are also meaningful when using another view of analogy. We address the accuracy of analogical inference for arbitrary Boolean functions and show that if a function is ε-close to an affine function, then the probability of making a wrong prediction is upper bounded by 4ε. This result is confirmed by an empirical study showing that the upper bound is tight. It highlights the specificity of analogical inference, also characterized in terms of the Hamming distance.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-02139765
Contributor : Miguel Couceiro <>
Submitted on : Saturday, May 25, 2019 - 4:31:41 PM
Last modification on : Thursday, October 24, 2019 - 2:44:12 PM

File

CouHugPraRicIJCAI2018WithKP-24...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02139765, version 1

Citation

Miguel Couceiro, Nicolas Hug, Henri Prade, Gilles Richard. Behavior of Analogical Inference w.r.t. Boolean Functions. IJCAI 2018 - 27th International Joint Conference on Artificial Intelligence, Jul 2018, Stockholm, Sweden. pp.2057--2063. ⟨hal-02139765⟩

Share

Metrics

Record views

35

Files downloads

750