Ramin Raziperchikolaei

Bio

I am a research scientist with expertise in machine learning. Since joining Rakuten in 2019, I have focused on recommendation systems and creating models that address real-world challenges, utilizing techniques such as deep learning to enhance the performance

I completed my PhD in the EECS Department of UC Merced, under supervision of Prof. Paul Maglio and Prof. Harish Bhat. I received my MSc in Artificial Intelligence from Sharif University of Technology.

Research Overview

My research is focused on machine learning and its applications in recommendation systems, language models, and computer vision. In my recent projects, I have developed deep models to tackle cold start problem in recommendation systems, deep self-supervised models on tabular data to extract user embeddings, and deep language models to extract item embeddings.

Publications

• Ramin Raziperchikolaei and Young-joo chung: "One-class recommendation systems with the hinge pairwise distance loss and orthogonal representations" RecSys, 2024. [To appear] [paper preprint]
• Ramin Raziperchikolaei and Young-joo chung: "A Recommendation System Framework to Generalize AutoRec and Neural Collaborative Filtering" ICDMW (workshop), 2022. [external link] [paper preprint]
• Ramin Raziperchikolaei and Young-joo chung: "Simultaneous Learning of the Inputs and Parameters in Neural Collaborative Filtering." BayLearn (workshop), 2022. [external link] [arXiv]
• Ramin Raziperchikolaei and Guannan Liang and Young-joo chung: "Shared Neural Item Representations for Completely Cold Start Problem" RecSys, 2021. [external link][paper preprint]
• Ramin Raziperchikolaei and Tianyu Li, and Young-joo chung: "Neural Representations in Hybrid Recommender Systems: Prediction versus Regularization" SIGIR, 2021. [external link] [paper preprint] [ slides] [poster] [Python code]
• Harish S. Bhat, Majerle Reeves, Ramin Raziperchikolaei: "Estimating Vector Fields from Noisy Time Series" ACSSC, 2020. [paper preprint]
• Ramin Raziperchikolaei, Harish S. Bhat: "A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation." ICML, 2019 [ external link] [paper preprint] [Supplementary material][Python code]
• Ramin Raziperchikolaei, Miguel Á. Carreira-Perpiñán: "Learning circulant support vector machines for fast image search." ICIP, 2017 [ external link] [paper preprint] [slides]
• Ramin Raziperchikolaei, Miguel Á. Carreira-Perpiñán: "Learning supervised binary hashing: Optimization vs diversity." ICIP, 2017 [ external link] [paper preprint] [poster]
• Ramin Raziperchikolaei, Miguel Á. Carreira-Perpiñán: "Learning Independent, Diverse Binary Hash Functions: Pruning and Locality." ICDM, 2016 [ external link ] [paper preprint] [slides] [Matlab code]
• Ramin Raziperchikolaei, Miguel Á. Carreira-Perpiñán: "Optimizing affinity-based binary hashing using auxiliary coordinates." NIPS, 2016 [ external link] [paper preprint] [ supplementary material] [ spotlight video] [poster] [Matlab code]
• Miguel Á. Carreira-Perpiñán, Ramin Raziperchikolaei: "An ensemble diversity approach to supervised binary hashing." NIPS, 2016 [ external link] [paper preprint] [ supplementary material] [ spotlight video] [poster] [Matlab code]
• Miguel Á. Carreira-Perpiñán, Ramin Raziperchikolaei: "Hashing with binary autoencoders." CVPR, 2015 [ external link] [paper preprint] [slides] [poster] [Matlab code]
• Ramin Raziperchikolaei, Mansour Jamzad: "Visual tracking using D2-clustering and particle filter." ISSPIT, 2012 [ external link] [paper preprint]
• Ali Bagheri-Khaligh, Ramin Raziperchikolaei , Mohsen Ebrahimi Moghaddam:"A new method for shot classification in soccer sports video based on SVM classifier." SSIAI, 2012 [ external link] [paper preprint]