RelNN: A Deep Neural Model for Relational Learning

Authors: Seyed Mehran Kazemi, David Poole

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Initial experiments on eight tasks over three real-world datasets show that Rel NNs are promising models for relational learning.
Researcher Affiliation Academia Seyed Mehran Kazemi, David Poole University of British Columbia Vancouver, Canada {smkazemi, poole}@cs.ubc.ca
Pseudocode No The paper describes mathematical formulations and processes but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes 1Code: https://github.com/Mehran-k/Rel NN
Open Datasets Yes Our first dataset is the Movielens 1M dataset (Harper and Konstan 2015)... Our second dataset is from PAKDD15 gender prediction competition2... Our third dataset contains all Chinese and Mexican restaurants in Yelp dataset challenge3...
Dataset Splits No For all experiments, we split the data into 80/20 percent train/test. No explicit mention of a separate validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup Yes We imposed a Laplacian prior on all our parameters (weights and numeric latent properties). For classification, we further regularized our model predictions towards the mean of the training set using a hyper-parameter λ as: Prob = λ mean + (1 λ) (Model Signal).