2019-FLAIRS’19 - Managing Popularity Bias in Recommender Systems with Personalized Re-ranking about adila

[hosseinfani]

@yogeswarl thank you. As we discussed, study how they measure the correctness of the reranked items.

[hosseinfani]

@Rounique @yogeswarl
I'm thinking of applying this paper or similar idea to team formation.

Currently, our code recommends top-k experts for a team. We can rerank the final top-k for fair team formation.

let me know of ur thought

[hosseinfani]

@yogeswarl thank you. please put those papers in your reading list and put their summaries in github. thanks.
Controlling Popularity Bias in Learning-to-Rank Recommendation is a good paper!

[yogeswarl]

@hosseinfani
They measure the correctness of the reranked items by 3 metrics

• Average Percentage of Long Tail Items (APLT) - a metric found in this paper 'https://dl.acm.org/doi/pdf/10.1145/3109859.3109912'
• Average Percentage of Long Tail Items (APLT): a metric found in this paper 'https://arxiv.org/pdf/1205.6700.pdf'
• Average Coverage of Long Tail items (ACLT): a custom metric to evaluate the exposure, long tail items get in the entire recommendation. They use this metric because, APLT could be high even for all users with the same set of long tail items.

They also measure the ranking accuracy to examine diversity-accuracy trade-off using standard Normalized Discounted cumulative Gain (NDCG).
There algorithm is 2 variants of the re-ranking algorithms, Binary xQuad and smooth xQuad
Binary xQuad is the original variant and the smooth xQuad takes ratio of items to the categories covered.
All the 3 metrics are required to conclude their results. they measure their algorithm with a cross validation split of 80-20.

Their is more accuracy loss in the algorithm but they tend to be fair in mitigating bias.

[Rounique]

I also read this carefully and now I guess we can discuss it more for applying it to our project.