# rixwew/pytorch-fm

Factorization Machine models in PyTorch

Repository: https://github.com/rixwew/pytorch-fm
Canonical: https://ross.abutalabs.com/products/pytorch-fm
Language: Python
License: MIT
License Family: permissive
Topics: factorization-machines, pytorch, deepfm, xdeepfm, autoint, ffm, fm, nfm, fnfm, dcn, pnn, movielens-dataset, criteo-dataset, avazu-dataset, ctr-prediction, collaborative-filtering, neural-collaborative-filtering, hofm
Last push: 2024-04-08T15:25:40+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2654, "days_push": 877, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1080, forks 229 (observed 2026-08-28T04:03:30.598544+00:00)

## What it is
A PyTorch library implementing a wide collection of factorization machine models (FM, FFM, DeepFM, xDeepFM, AutoInt, NFM, DCN, and more) for click-through rate prediction and recommendation. It also bundles loaders for common benchmark datasets like MovieLens, Criteo, and Avazu.

## Use cases
- train factorization machine models in pytorch
- run ctr prediction experiments with deepfm or xdeepfm
- benchmark feature interaction models on criteo and avazu datasets
- implement neural collaborative filtering
- compare recommender model auc on movielens
- learn how factorization machines are implemented

## When to choose
- you need many factorization machine variants in one pytorch package
- you want reproducible baselines on standard CTR datasets
- you are researching or teaching feature interaction models

## When to avoid
- you need a production recommender system with serving infrastructure
- you work outside PyTorch or need distributed large-scale training
- you need actively developed features beyond the existing model set

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, data-science
- platform: python
- tags: factorization-machines, ctr-prediction, recommender-systems, pytorch, deepfm, collaborative-filtering, feature-interaction, recommendation

## Member repositories
- rixwew/pytorch-fm (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:30.598544+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:00.549432+00:00, confidence not recorded.
  - readme: https://github.com/rixwew/pytorch-fm (fetched 2026-08-28T04:03:30.598544+00:00, sha 0df790eea013)
- Data as of 2026-08-30T08:39:29.467469+00:00.