Repository for Multimodal AutoML Benchmark

Overview

Benchmarking Multimodal AutoML for Tabular Data with Text Fields

Repository for the NeurIPS 2021 Dataset Track Submission "Benchmarking Multimodal AutoML for Tabular Data with Text Fields" (Link, Full Paper with Appendix). An earlier version of the paper, called "Multimodal AutoML on Structured Tables with Text Fields" (Link) has been accepted by ICML 2021 AutoML workshop as Oral. As we have since updated the benchmark with more datasets, the version used in the AutoML workshop paper has been archived at the icml_workshop branch.

This benchmark contains a diverse collection of tabular datasets. Each dataset contains numeric/categorical as well as text columns. The goal is to evaluate the performance of (automated) ML systems for supervised learning (classification and regression) with such multimodal data. The folder multimodal_text_benchmark/scripts/benchmark/ provides Python scripts to run different variants of the AutoGluon and H2O AutoML tools on the benchmark.

Datasets used in the Benchmark

Here's a brief summary of the datasets in our benchmark. Each dataset is described in greater detail in the multimodal_text_benchmark/ folder.

ID key #Train #Test Task Metric Prediction Target
prod product_sentiment_machine_hack 5,091 1,273 multiclass accuracy sentiment related to product
salary data_scientist_salary 15,84 3961 multiclass accuracy salary range in data scientist job listings
airbnb melbourne_airbnb 18,316 4,579 multiclass accuracy price of Airbnb listing
channel news_channel 20,284 5,071 multiclass accuracy category of news article
wine wine_reviews 84,123 21,031 multiclass accuracy variety of wine
imdb imdb_genre_prediction 800 200 binary roc_auc whether film is a drama
fake fake_job_postings2 12,725 3,182 binary roc_auc whether job postings are fake
kick kick_starter_funding 86,052 21,626 binary roc_auc will Kickstarter get funding
jigsaw jigsaw_unintended_bias100K 100,000 25,000 binary roc_auc whether comments are toxic
qaa google_qa_answer_type_reason_explanation 4,863 1,216 regression r2 type of answer
qaq google_qa_question_type_reason_explanation 4,863 1,216 regression r2 type of question
book bookprice_prediction 4,989 1,248 regression r2 price of books
jc jc_penney_products 10,860 2,715 regression r2 price of JC Penney products
cloth women_clothing_review 18,788 4,698 regression r2 review score
ae ae_price_prediction 22,662 5,666 regression r2 American-Eagle item prices
pop news_popularity2 24,007 6,002 regression r2 news article popularity online
house california_house_price 24,007 6,002 regression r2 sale price of houses in California
mercari mercari_price_suggestion100K 100,000 25,000 regression r2 price of Mercari products

License

The versions of datasets in this benchmark are released under the CC BY-NC-SA license. Note that the datasets in this benchmark are modified versions of previously publicly-available original copies and we do not own any of the datasets in the benchmark. Any data from this benchmark which has previously been published elsewhere falls under the original license from which the data originated. Please refer to the licenses of each original source linked in the multimodal_text_benchmark/README.md.

Install the Benchmark Suite

cd multimodal_text_benchmark
# Install the benchmarking suite
python3 -m pip install -U -e .

You can do a quick test of the installation by going to the test folder

cd multimodal_text_benchmark/tests
python3 -m pytest test_datasets.py

To work with one of the datasets, use the following code:

from auto_mm_bench.datasets import dataset_registry

print(dataset_registry.list_keys())  # list of all dataset names
dataset_name = 'product_sentiment_machine_hack'

train_dataset = dataset_registry.create(dataset_name, 'train')
test_dataset = dataset_registry.create(dataset_name, 'test')
print(train_dataset.data)
print(test_dataset.data)

To access all datasets that comprise the benchmark:

from auto_mm_bench.datasets import create_dataset, TEXT_BENCHMARK_ALIAS_MAPPING

for dataset_name in list(TEXT_BENCHMARK_ALIAS_MAPPING.values()):
    print(dataset_name)
    dataset = create_dataset(dataset_name)

Run Experiments

Go to multimodal_text_benchmark/scripts/benchmark to see how to run some baseline ML methods over the benchmark.

References

BibTeX entry of the ICML Workshop Version:

@article{agmultimodaltext,
  title={Multimodal AutoML on Structured Tables with Text Fields},
  author={Shi, Xingjian and Mueller, Jonas and Erickson, Nick and Li, Mu and Smola, Alexander},
  journal={8th ICML Workshop on Automated Machine Learning (AutoML)},
  year={2021}
}
Owner
Xingjian Shi
Xingjian Shi
Python code for the paper How to scale hyperparameters for quickshift image segmentation

How to scale hyperparameters for quickshift image segmentation Python code for the paper How to scale hyperparameters for quickshift image segmentatio

0 Jan 25, 2022
The official repository for "Revealing unforeseen diagnostic image features with deep learning by detecting cardiovascular diseases from apical four-chamber ultrasounds"

Revealing unforeseen diagnostic image features with deep learning by detecting cardiovascular diseases from apical four-chamber ultrasounds The why Im

3 Mar 29, 2022
Deep generative models of 3D grids for structure-based drug discovery

What is liGAN? liGAN is a research codebase for training and evaluating deep generative models for de novo drug design based on 3D atomic density grid

Matt Ragoza 152 Jan 03, 2023
CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification (ICCV2021)

CM-NAS Official Pytorch code of paper CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification in ICCV2021. Vis

JDAI-CV 40 Nov 25, 2022
A large-scale benchmark for co-optimizing the design and control of soft robots, as seen in NeurIPS 2021.

Evolution Gym A large-scale benchmark for co-optimizing the design and control of soft robots. As seen in Evolution Gym: A Large-Scale Benchmark for E

121 Dec 14, 2022
GLM (General Language Model)

GLM GLM is a General Language Model pretrained with an autoregressive blank-filling objective and can be finetuned on various natural language underst

THUDM 421 Jan 04, 2023
FlowTorch is a PyTorch library for learning and sampling from complex probability distributions using a class of methods called Normalizing Flows

FlowTorch is a PyTorch library for learning and sampling from complex probability distributions using a class of methods called Normalizing Flows.

Meta Incubator 272 Jan 02, 2023
A Jinja extension (compatible with Flask and other frameworks) to compile and/or compress your assets.

A Jinja extension (compatible with Flask and other frameworks) to compile and/or compress your assets.

Jayson Reis 94 Nov 21, 2022
BOVText: A Large-Scale, Multidimensional Multilingual Dataset for Video Text Spotting

BOVText: A Large-Scale, Bilingual Open World Dataset for Video Text Spotting Updated on December 10, 2021 (Release all dataset(2021 videos)) Updated o

weijiawu 47 Dec 26, 2022
Deep Q-network learning to play flappybird.

AI Plays Flappy Bird I've trained a DQN that learns to play flappy bird on it's own. Try the pre-trained model First install the pip requirements and

Anish Shrestha 3 Mar 01, 2022
Pytorch-diffusion - A basic PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

PyTorch implementation of 'Denoising Diffusion Probabilistic Models' This reposi

Arthur Juliani 76 Jan 07, 2023
Test-Time Personalization with a Transformer for Human Pose Estimation, NeurIPS 2021

Transforming Self-Supervision in Test Time for Personalizing Human Pose Estimation This is an official implementation of the NeurIPS 2021 paper: Trans

41 Nov 28, 2022
Code for paper: "Spinning Language Models for Propaganda-As-A-Service"

Spinning Language Models for Propaganda-As-A-Service This is the source code for the Arxiv version of the paper. You can use this Google Colab to expl

Eugene Bagdasaryan 16 Jan 03, 2023
Noether Networks: meta-learning useful conserved quantities

Noether Networks: meta-learning useful conserved quantities This repository contains the code necessary to reproduce experiments from "Noether Network

Dylan Doblar 33 Nov 23, 2022
Si Adek Keras is software VR dangerous object detection.

Si Adek Python Keras Sistem Informasi Deteksi Benda Berbahaya Keras Python. Version 1.0 Developed by Ananda Rauf Maududi. Developed date: 24 November

Ananda Rauf 1 Dec 21, 2021
Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation

Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation By: Zayd Hammoudeh and Daniel Lowd Paper: Arxiv Preprint Coming soo

Zayd Hammoudeh 2 Oct 08, 2022
Codes for our paper The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders published to EMNLP 2021.

The Stem Cell Hypothesis Codes for our paper The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders published to EMNLP

Emory NLP 5 Jul 08, 2022
Learning with Subset Stacking

Learning with Subset Stacking (LESS) LESS is a new supervised learning algorithm that is based on training many local estimators on subsets of a given

S. Ilker Birbil 19 Oct 04, 2022
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

VAENAR-TTS - PyTorch Implementation PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

Keon Lee 67 Nov 14, 2022
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation (ACM MM 2020)

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation (ACM MM 2020) Official implementation of: Forest R-CNN: Large-Vo

Jialian Wu 54 Jan 06, 2023