2005 

• 𝐎𝐧𝐞𝐄𝐧𝐜𝐨𝐝𝐞𝐫 — a lightweight, modular, and efficient framework for multimodal learning.

🛠️ 𝐓𝐫𝐲 𝐢𝐭 𝐲𝐨𝐮𝐫𝐬𝐞𝐥𝐟:

🔗 Demo: https://lnkd.in/eCut8jYJ

💻 Code: https://lnkd.in/ehcpeG2W

📓 Notebook: https://lnkd.in/eUrzQjHt

📄 Published paper: https://lnkd.in/eVMxJuHu

2024

• For those seeking efficiency, we've developed SCB-Norm-Base, a lightweight version with fewer parameters to tune. Perfect for scenarios where resource constraints are a concern!

🚀 PyPI Packages:

- PyTorch: [torch-cluster-based-norm](https://lnkd.in/g4hS-mCU)

- TensorFlow: [tf-cluster-based-norm](https://lnkd.in/gmwAFbDX)

- Keras: [keras-cluster-based-norm](https://lnkd.in/gSEurRbV)

🔗 GitHub Repository: Explore our codebase on GitHub: [cluster-based-norm](https://lnkd.in/gsJkAuHW)

• Verbalizer benchmarking for text classification: https://github.com/quang-anh-nguyen/verbalizer_benchmark

This repository contains the code for benchmarking verbalizer baselines for text classification problems, published at LREC-COLING 2024.

• DisCGS : https://github.com/redakhoufache/DisCGS

This repository contains our implementation of the distributed collapsed Gibbs sampler for Dirichlet Process Mixture Model inference, proposed in the paper "Distributed Collapsed Gibbs Sampler for Dirichlet Process Mixture Models in Federated Learning" (Accepted to SIAM International Conference on Data Mining (SDM24)).

• Distributed-NPLBM : https://github.com/redakhoufache/Distributed-NPLBM

This repository contains our implementation of DisNPLBM proposed in the paper "Distributed MCMC inference for Bayesian Non-Parametric Latent Block Model" (accepted to The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2024)), arxiv.

2023 

• TabSRA: An Attention based Self-Explainable Model for Tabular Learning

https://github.com/unsupervise/TabSRA  or

https://github.com/anselmeamekoe/TabSRA

• MTS-CGAN: Conditional Generative Adversarial Network for Multivariate Time Series

https://github.com/unsupervise/MTS-CGAN or

https://github.com/MadaneA/MTS-CGAN.

2021-2022 

• This code implements three model based block clustering methods. 

https://github.com/EtienneGof/MultiCoclustering

These models are based on the Dirichlet Process Mixture Model (DPMM, used for univariate dataset clustering) and extends it to multivariate datasets.

• SOMperf: SOM performance metrics and quality indices

• skstab is a module for clustering stability analysis in Python with a scikit-learn compatible API  

https://github.com/FlorentF9/skstab

• Spark Time Series Set data analysis

https://github.com/spark-tss/spark-tss

• 2019: Deep Embedded Self-Organizing Map (DESOM) model,(Unsupervised Deep Learning) Git

https://github.com/FlorentF9/DESOM

• 02/2018: https://github.com/Clustering4Ever/Clustering4Ever

Its Big Data Clustering Library (API) gathering clustering algorithms and quality indexes in Scala and Spark/Scala. Don't hesitate to ask questions or make recommendations in our Gitter. It is also in SparkPackages.

Some examples using the C4E API  are a avalaible here 

02/2015

• GitHub : https://github.com/Spark-clustering-notebook/coliseum

• Docker : https://hub.docker.com/r/spartakus/coliseum/

For more informations about "Data Science & Big data" in LIPN

• Wiki : https://lipn.univ-paris13.fr/bigdata/