An Axiomatic Approach to Link Prediction

Authors: Sara Cohen, Aviv Zohar

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We draw upon the motivation used in characterizations of ranking algorithms, as well as other celebrated results from social choice, and present an axiomatic basis for link prediction. This approach seeks to deconstruct each function into basic axioms, or properties, that make explicit its underlying assumptions. ... The second part of each proof is to show that the set of given properties uniquely defines the specific link prediction function (i.e., there exist no additional functions satisfying the set of properties). This type of proof is typically more intricate.
Researcher Affiliation Academia Sara Cohen and Aviv Zohar Rachel and Selim Benin School of Computer Science and Engineering, Hebrew University of Jerusalem, Jerusalem, Israel {sara, avivz}@cs.huji.ac.il
Pseudocode No The paper defines functions and properties formally but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statements about releasing open-source code, nor does it include links to a code repository.
Open Datasets No The paper is theoretical, characterizing link prediction functions. It does not describe experiments involving datasets for training or evaluation in the context of the authors' own work. It mentions 'data sets' in the context of prior empirical work.
Dataset Splits No The paper is theoretical and does not conduct empirical experiments, therefore, it does not specify training, validation, or test dataset splits.
Hardware Specification No As a theoretical paper focused on axiomatic characterization, it does not describe experimental setups or require specific hardware, and thus no hardware specifications are mentioned.
Software Dependencies No As a theoretical paper, it does not specify any software dependencies with version numbers for reproducing experimental results.
Experiment Setup No As a theoretical paper, it does not detail any experimental setup, hyperparameters, or training configurations.