{"id":28641670,"url":"https://github.com/autogluon/neurips2022-autogluon-workshop","last_synced_at":"2025-10-07T06:23:10.756Z","repository":{"id":295517344,"uuid":"729630447","full_name":"autogluon/neurips2022-autogluon-workshop","owner":"autogluon","description":"AutoGluon NeurIPS 2022 presentation material ","archived":false,"fork":false,"pushed_at":"2023-12-09T20:54:42.000Z","size":865,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-06-12T21:55:01.404Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/autogluon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-12-09T20:49:12.000Z","updated_at":"2023-12-09T20:54:45.000Z","dependencies_parsed_at":"2025-05-26T15:04:22.531Z","dependency_job_id":null,"html_url":"https://github.com/autogluon/neurips2022-autogluon-workshop","commit_stats":null,"previous_names":["autogluon/neurips2022-autogluon-workshop"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/autogluon/neurips2022-autogluon-workshop","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fneurips2022-autogluon-workshop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fneurips2022-autogluon-workshop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fneurips2022-autogluon-workshop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fneurips2022-autogluon-workshop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/autogluon","download_url":"https://codeload.github.com/autogluon/neurips2022-autogluon-workshop/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fneurips2022-autogluon-workshop/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266087790,"owners_count":23874519,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-12T21:42:22.824Z","updated_at":"2025-10-07T06:23:05.722Z","avatar_url":"https://github.com/autogluon.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AutoGluon: Empowering (Multimodal) AutoML for the Next 10 Million Users\n\nAutomated machine learning (AutoML) offers the promise of translating raw data into accurate predictions without the need for \nsignificant human effort, expertise, and manual experimentation. In this workshop, we introduce [AutoGluon](https://github.com/autogluon/autogluon), \na state-of-the-art and easy-to-use toolkit that empowers *multimodal* AutoML. Different from most AutoML systems that focus on solving tabular tasks \ncontaining categorical and numerical features, we consider supervised learning tasks on various types of data including tabular \nfeatures, text, image, time series, as well as their combinations. We will introduce the real-world problems that AutoGluon can help you \nsolve within three lines of code and the fundamental techniques adopted in the toolkit.\nRather than diving deep into the mechanisms underlining each individual ML models, \nwe emphasize on how you can take advantage of a diverse collection of models to build an automated ML pipeline.\nOur workshop will also emphasize on the techniques behind automatically building and training deep learning models, \nwhich are powerful yet cumbersome to manage manually.\n\nJoin us at the [NeurIPS 2022](https://nips.cc/) located at New Orleans Ernest N. Morial Convention Center on Monday, November 28 at 2:00pm, CST in \nRoom 293.\n\n*Note: Github repository for this website is available at https://github.com/autogluon/neurips2022-autogluon-workshop* . \n\nPlease take a simple [survey](https://www.surveymonkey.com/r/TVYBFG3) (less than 1 minute) for feature request and feedback, we appreciate your input.\n\n\n## Schedule\n\nFor each section, there will be a 10-15min QA at the end of section. In addition, there will be [additional hands-on notebooks](#hands-on-notebooks) after \neach session that people can try out asynchronously.\n\n| Topic | Speaker | Duration (CST timezone) | Slides | Cheatsheet |\n|--------------------------------------------------------|---------------------------------------------------------------------------------------|-------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Introduction + AutoGluon Tabular](#autogluon-tabular) | [Nick Erickson](https://github.com/Innixma) | 2:00PM -- 2:55PM | [link](https://docs.google.com/presentation/d/1whJdw8W0IixwFyRna13AjqlFKwO9ufsR/edit?usp=sharing\u0026ouid=117434028345007023633\u0026rtpof=true\u0026sd=true) | [![tabular-cheatsheet](https://raw.githubusercontent.com/Innixma/autogluon-doc-utils/main/docs/cheatsheets/stable/autogluon-cheat-sheet.jpeg)](https://nbviewer.org/github/Innixma/autogluon-doc-utils/blob/main/docs/cheatsheets/stable/autogluon-cheat-sheet.pdf) [docs](https://auto.gluon.ai/stable/tutorials/tabular_prediction/index.html) |\n| Break | - | 2:55PM -- 3:05PM | - | |\n| [AutoGluon Multimodal](#autogluon-multimodal) | [Xingjian Shi](https://github.com/sxjscience), [Yi Zhu](https://github.com/bryanyzhu) | 3:05PM -- 4:00PM | [link](https://docs.google.com/presentation/d/1SlHVzaWtN-75m6mmvapeu4-C2Id7V5wO/edit?usp=sharing\u0026ouid=117434028345007023633\u0026rtpof=true\u0026sd=true) | [![multimodal-cheatsheet](https://automl-mm-bench.s3-accelerate.amazonaws.com/cheatsheet/v0.6.0/AutoGluon_Multimodal_Cheatsheet_v0.6.0.png)](https://automl-mm-bench.s3-accelerate.amazonaws.com/cheatsheet/v0.6.0/AutoGluon_Multimodal_Cheatsheet_v0.6.0.pdf) [docs](https://auto.gluon.ai/stable/tutorials/multimodal/index.html) |\n| Break | - | 4:00PM -- 4:10PM | - | |\n| [AutoGluon Timeseries](#autogluon-timeseries) | [Caner Turkmen](https://github.com/canerturkmen) | 4:10PM -- 4:50PM | [link](https://docs.google.com/presentation/d/1AwZFuUWFT_Dp2wFLh9dk_RYLaYlsbxpN/edit?usp=sharing\u0026ouid=117434028345007023633\u0026rtpof=true\u0026sd=true) | [![timeseries-cheatsheet](https://autogluon-timeseries-datasets.s3.us-west-2.amazonaws.com/public/autogluon_timeseries_cheatsheet.png)](https://autogluon-timeseries-datasets.s3.us-west-2.amazonaws.com/public/autogluon_timeseries_cheatsheet.pdf) [docs](https://auto.gluon.ai/stable/tutorials/timeseries/index.html) |\n| Additional QA + Feedback | All speakers | 4:50PM -- 5:00PM | - | |\n\n\n## Section Outline and Materials\n\n### AutoGluon Tabular\n\n- AutoML Basics: Discussion of core AutoML principles\n- History of competition ML and how it influenced the design of modern AutoML systems\n- Discussion of model combination strategies (stacking, bagging, model aggregation)\n- Constraint satisfaction and engineering for a performance envelope (accuracy, speed, compute resources)\n- Benchmark comparisons showcasing the advancement of AutoML systems in recent years both compared to earlier AutoML systems and human data scientists (4 AutoML frameworks, 104 OpenML datasets, 10 Kaggle datasets)\n\n\n### AutoGluon Multimodal\n\n- Real-world multimodal problems (life beyond captioning images)\n- Foundation models for image and text\n- Fusion techniques \u0026 ensemble FMs / tabular models \n- Object detection\n- Multimodal matching\n- Advanced topics\n - Training: Parameter-efficient finetuning\n - Deployment: Model distillation\n - Hyper-parameter optimization\n- Hands-on notebooks + QA: [notebooks](./notebooks)\n\n### AutoGluon Timeseries\n\n- Time series forecasting in a nutshell\n- An overview of machine learning for forecasting\n- AutoML in time series and unique challenges\n- Forecasting with AutoGluon-TimeSeries\n- Looking forward in time series AutoML\n- Hands-on notebooks + QA: [notebooks](./notebooks)\n\n### Hands-on Notebooks\n\nFor hands-on tutorials, we provide notebooks for you to try out AutoGluon via [SageMaker Studio Lab](https://aws.amazon.com/sagemaker/studio-lab/) or [Google Colab](https://colab.research.google.com/).\n\nAll notebooks can be found in [notebooks](./notebooks).\n\n**Checkout [AutoGluon Website](https://auto.gluon.ai/) and get started!**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautogluon%2Fneurips2022-autogluon-workshop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fautogluon%2Fneurips2022-autogluon-workshop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautogluon%2Fneurips2022-autogluon-workshop/lists"}