Skip to content

Latest commit

 

History

History
102 lines (59 loc) · 3.09 KB

model_card.md

File metadata and controls

102 lines (59 loc) · 3.09 KB
Raw

Model Card for RecFusion

A Binomial / Gaussian Diffusion Process for 1D Data for Recommendation

Model Details

Model Description

A Binomial / Gaussian Diffusion Process for 1D Data for Recommendation

  • Developed by: Anonymized
  • Model type: Recommendation model
  • License: unknown

Uses

Direct Use

(i) non-sequential (ii) Top-K recommendation with (iii) binary feedback

Out-of-Scope Use

Recommendation setups that violate assumptions (i)-(iii).

Bias, Risks, and Limitations

Significant research has explored bias and fairness issues with language models (see, e.g., Li et al. (2021)). Predictions generated by the model may for example unfairly favor more active users and more popular items.

Training Details

Training Data

MovieLens1M, MovieLens10M, MovieLens25M, Netflix

Preprocessing

(i) filter out users with fewer than five items, and items with fewer than five interactions (ii) Users are split into train, validation and test sets (0.8 / 0.1 / 0.1), with the training employing the entire history. For validation and test sets, a partial history is fed to the recommender, with a held-out set being used to evaluate the resulting recommendation. [a.k.a. strong generalization] (iii) binarize feedback: ratings above 3 are encoded as 1, and zero otherwise.

Evaluation

Metrics

Recall@20, Recall@50, NDCG@100

Results

Dataset Model Recall@20 Recall@50 NDCG@100
MovieLens25M Random 0.13 0.30 0.24
Popularity 16.63 24.43 19.69
\textbf{RecFusion} 33.21 45.44 37.31
CODIGEM 34.05 45.84 37.90
MultVAE 35.12 48.09 39.12
EASE 40.02 52.71 43.84
Netflix Random 0.18 0.32 0.31
Popularity 11.73 17.48 15.89
CODIGEM 25.54 33.48 29.08
\textbf{RecFusion} 29.68 37.63 32.87
MultVAE 31.61 40.61 35.23
EASE 36.19 44.49 39.35

Environmental Impact

  • Hardware Type: More information needed
  • Hours used: ~ 200 (including hyperparameter tuning)
  • Cloud Provider: Azure
  • Compute Region: West Europe
  • Carbon Emitted: ~ 35 kg CO2 eq.

Carbon emissions were estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Technical Specifications

Model Architecture and Objective

Either one of MLP, MLP+T, MLP+Var, U-Net1D, U-Net2D

Compute Infrastructure

Databricks ML clusters version 13 ML with sparktrials

Citation

BibTeX:

Anonymized

APA:

Anonymized

Model Card Contact

Anonymized