Stationary Algorithmic Balancing For Dynamic Email Re-Ranking Problem logo

Stationary Algorithmic Balancing For Dynamic Email Re-Ranking Problem

Email platforms need to generate personalized rankings of emails that satisfy user preferences, which may vary over time.

GitHub Link

The GitHub link is https://github.com/jylevangeline/mosr

Introduce

The GitHub repository "JYLEvangeline/MOSR" presents an algorithmic solution, MOSR, for the dynamic email re-ranking problem, as accepted by KDD '23. The paper's link and dataset download address are provided. The code for the solution involves generating a .json file through "check_data_distance_2.py" and running "model_new.py" with specific parameters for EnronA and EnronB datasets. The necessary dataset files are included in the repository. Email platforms need to generate personalized rankings of emails that satisfy user preferences, which may vary over time.

Content

Our paper could be viewd at (https://dl.acm.org/doi/pdf/10.1145/3580305.3599909) The dataset could be download in https://www.cs.cmu.edu/~enron/. Please put it in data/ data/organization2.csv is crawled by us. And it is already in data/ folder. python model_new.py --md 10 -v 0 -lr 0.99 python model_new.py --md 10 -v 1 -lr 0.99

Alternatives & Similar Tools

LongLLaMA-handle very long text contexts, up to 256,000 tokens logo

LongLLaMA is a large language model designed to handle very long text contexts, up to 256,000 tokens. It's based on OpenLLaMA and uses a technique called Focused Transformer (FoT) for training. The repository provides a smaller 3B version of LongLLaMA for free use. It can also be used as a replacement for LLaMA models with shorter contexts.