Implementation for the PREPRec paper, accepted at Recsys 2024. Our method enables cross-domain, cross-user zero-shot transfer competitive with in-domain SOTA models.
Quick start: download Tools and Home Improvement
and Office Products
datasets from "Small" subsets for experimentation section of here and rename as amazon_tool.csv
and amazon_office.csv
under data/amazon
directory. then run data/preprocess.sh
for preprocessing steps that need to be run before training. then after creating filler folders, sample.sh
has some examples for running and evaluating models
Coming soon: env dependencies; exact replication scripts for each of the five datasets we evaluate on.
Credits: Code is based off this pytorch SASRec implementation, with code also taken/repurposed from here, here, here and here.