Link Prediction With Personalized Social Influence

Authors: Zepeng Huo, Xiao Huang, Xia Hu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Through comprehensive experiments, we demonstrate that the proposed framework can perform better than the state-of-the-art methods on different real-world networks.
Researcher Affiliation Academia Zepeng Huo,1 Xiao Huang,1 Xia Hu1,2 1Department of Computer Science and Engineering, Texas A&M University 2Center for Remote Health Technologies and Systems, Texas A&M Engineering Experiment Station
Pseudocode No The paper describes the proposed framework and algorithms using mathematical equations and textual explanations, but it does not include a formally labeled "Pseudocode" or "Algorithm" block.
Open Source Code No The paper does not include any statement about releasing source code or a link to a code repository for the methodology described.
Open Datasets Yes We use two publicly available datasets in our experiment: URL Twitter dataset (Hodas and Lerman 2014) and Higgs Twitter dataset (Leskovec and Krevl 2014).
Dataset Splits No The paper specifies training and testing splits (e.g., "10%, 20%, 40%, 60%" for training, and remaining instances for test), but it does not explicitly mention a separate "validation" set or its split percentage/size.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. It only discusses the datasets and experimental setup.
Software Dependencies No The paper does not specify any software dependencies or their version numbers that would be needed to reproduce the experiments (e.g., Python, PyTorch, TensorFlow versions, or specific library versions).
Experiment Setup Yes We set the learning rate as 0.01 and regularization parameters of representations as 0.025. Numerically, for the coefficients α = {α0, α1, α2} in Eqs. (5) and (7), a negative coefficient was more likely because of over-fitting than the situation that user uj will suppress user ui s activities. Therefore, if any coefficient happens to be negative in likelihood function, it will be rejected.