CLNTM - Contrastive Learning for Neural Topic Model

Related tags

Deep Learning CLNTM
Overview

Contrastive Learning for Neural Topic Model

This repository contains the implementation of the paper Contrastive Learning for Neural Topic Model.

Thong Nguyen, Luu Anh Tuan (NeurIPS 2021)

Teaser image In this work, we target the problem of capturing meaningful representations through modeling the relations among samples from a mathematical perspective and propose a novel contrastive objective to train the neural topic model, along with the optimization of the variational lower bound. In our contrastive learning framework, we introduce a novel sampling strategy that is motivated by human behavior when comparing numerous documents. Our results show that capturing mutual information between the prototype and its positive sample provides a strong foundation for constructing coherent topics, while differentiating the prototype from the negative samples plays a less fundamental role.

@inproceedings{
nguyen2021contrastive,
title={Contrastive Learning for Neural Topic Model},
author={Thong Thanh Nguyen and Anh Tuan Luu},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=NEgqO9yB7e}
}

Requirements

  • python3
  • pandas
  • gensim
  • numpy
  • torchvision
  • pytorch 1.7.0
  • scipy

How to Run

  1. Download and put the dataset in the data folder: https://drive.google.com/file/d/1JeeUCzBRQqJUvdWGDN7aMRvIoBAIbZIc/view?usp=sharing
  2. Train the model by running ./scripts/train_models/run_{dataset}_{topk}.sh
  3. Evaluate the model via executing ./scripts/evaluate/run_{dataset}_npmi_{topk}.sh

Acknowledgement

Our implementation is based on the official code of SCHOLAR.

You might also like...
The official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
The official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

This repository is the official PyTorch implementation of SAINT. Find the paper on arxiv SAINT: Improved Neural Networks for Tabular Data via Row Atte

Gowthami Somepalli 284 Dec 21, 2022
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021.
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021.

Dense Contrastive Learning for Self-Supervised Visual Pre-Training This project hosts the code for implementing the DenseCL algorithm for se

Xinlong Wang 491 Jan 3, 2023
pytorch implementation of
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Unofficial implementation: MoCo: Momentum Contrast for Unsupervised Visual Representation Learning (Paper) InsDis: Unsupervised Feature Learning via N

Zhiqiang Shen 16 Nov 4, 2020
CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning
CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning

CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning This repository contains the code and relevant instructions

XiaoMing 5 Aug 19, 2022
In this project we investigate the performance of the SetCon model on realistic video footage. Therefore, we implemented the model in PyTorch and tested the model on two example videos.
In this project we investigate the performance of the SetCon model on realistic video footage. Therefore, we implemented the model in PyTorch and tested the model on two example videos.

Contrastive Learning of Object Representations Supervisor: Prof. Dr. Gemma Roig Institutions: Goethe University CVAI - Computational Vision & Artifici

Dirk Neuhäuser 6 Dec 8, 2022
Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function
Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

El Bruno 3 Mar 30, 2022
Cancer-and-Tumor-Detection-Using-Inception-model - In this repo i am gonna show you how i did cancer/tumor detection in lungs using deep neural networks, specifically here the Inception model by google.
Cancer-and-Tumor-Detection-Using-Inception-model - In this repo i am gonna show you how i did cancer/tumor detection in lungs using deep neural networks, specifically here the Inception model by google.

Cancer-and-Tumor-Detection-Using-Inception-model In this repo i am gonna show you how i did cancer/tumor detection in lungs using deep neural networks

Deepak Nandwani 1 Jan 1, 2022
Contrastive Learning Inverts the Data Generating Process
Contrastive Learning Inverts the Data Generating Process

Official code to reproduce the results and data presented in the paper Contrastive Learning Inverts the Data Generating Process.

null 71 Nov 25, 2022
Code for CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

CoMatch: Semi-supervised Learning with Contrastive Graph Regularization (Salesforce Research) This is a PyTorch implementation of the CoMatch paper [B

Salesforce 107 Dec 14, 2022
Comments
  • details to achieve the paper results

    details to achieve the paper results

    Hello! Thanks for your great job!

    I have some questions about the details of the results. I want to replicate the paper results and run the code like this: python run_scholar.py data/20ng/processed/ -k 50 --topk 15 --test-prefix test --device 0 --o ./outputs/scholar/20ng_50_15 --epochs 500 --model trueContrastiveScholar --dist 0 and get result 0.3298 +- 0.0024 (5 runs)，a little lower than your result 0.334 +- 0.004.

    I find that your code is based on the Scholar model, so I wonder if you have incorporated the metadata, such as labels, covariates, and/or word2vec embeddings. If so, how did you use them? Thanks all.

    opened by lei-liu1 2
  • Something wrong in scholar.py?

    Something wrong in scholar.py?

    In the torchContrastiveScholar class,I saw the contrastive_loss in _loss() function.But in the torchTrueContrastiveScholar class, the _loss() function only includes NL and KLD.Negative part and positive part do not work in the follow-up code.So the torchTrueContrastiveScholar class is just VAE.

    opened by Rp12138 0
  • Adaptive scheduling code

    Adaptive scheduling code

    Hello! Thanks for your great job!

    I have some questions about the details of the results. I want to replicate the paper results and run the code like this: python run_scholar.py data/imdb/processed/ -k 50 --topk 15 --test-prefix test --device 0 --o ./outputs/scholar/imdb_50_15 --epochs 500 --model trueContrastiveScholar --dist 0 and get result 0.17~0.18(5 runs), lower than your result 0.197 ± 0.006 in the paper.

    I find that your code does not implement adaptive scheduling β as described in your paper. If so, can you release the code?? Thanks all.

    opened by liuh236 0
Owner
Thong Thanh Nguyen
...
Thong Thanh Nguyen
GitHub
SUPERVISED-CONTRASTIVE-LEARNING-FOR-PRE-TRAINED-LANGUAGE-MODEL-FINE-TUNING - The Facebook paper about fine tuning RoBERTa with contrastive loss

"# SUPERVISED-CONTRASTIVE-LEARNING-FOR-PRE-TRAINED-LANGUAGE-MODEL-FINE-TUNING" i

Saeed Lotfi 28 Dec 12, 2022
Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Noise Contrastive Estimation for pyTorch Overview This repository contains a re-implementation of the Noise Contrastive Estimation algorithm, implemen

Denis Emelin 42 Nov 24, 2022
Topic Modelling for Humans

gensim – Topic Modelling in Python Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. Targ

RARE Technologies 13.8k Jan 3, 2023
A Topic Modeling toolbox

Topik A Topic Modeling toolbox. Introduction The aim of topik is to provide a full suite and high-level interface for anyone interested in applying to

Anaconda, Inc. (formerly Continuum Analytics, Inc.) 93 Dec 1, 2022
This is a model made out of Neural Network specifically a Convolutional Neural Network model

This is a model made out of Neural Network specifically a Convolutional Neural Network model. This was done with a pre-built dataset from the tensorflow and keras packages. There are other alternative libraries that can be used for this purpose, one of which is the PyTorch library.

null 9 Oct 18, 2022
This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

The Neural Process Family This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CN

DeepMind 892 Dec 28, 2022
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation(mCOLT/mRASP2), ACL2021

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation(mCOLT/mRASP2), ACL2021 The code for training mCOLT/mRASP2, a multilingua

null 104 Jan 1, 2023
This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).

NeurIPS 2021 (Spotlight): Task-Adaptive Neural Network Search with Meta-Contrastive Learning This is an official PyTorch implementation of Task-Adapti

Wonyong Jeong 15 Nov 21, 2022
[IJCAI-2021] A benchmark of data-free knowledge distillation from paper "Contrastive Model Inversion for Data-Free Knowledge Distillation"

DataFree A benchmark of data-free knowledge distillation from paper "Contrastive Model Inversion for Data-Free Knowledge Distillation" Authors: Gongfa

ZJU-VIPA 47 Jan 9, 2023
The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021] Release Notes The offical PyTorch implementation of NeMo, p

Angtian Wang 76 Nov 23, 2022