-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
eb6fc89
commit 3af6835
Showing
27 changed files
with
3,281 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,275 @@ | ||
| <!DOCTYPE html> | ||
| <html> | ||
| <head> | ||
| <meta charset="utf-8"> | ||
| <!-- Meta tags for social media banners, these should be filled in appropriatly as they are your "business card" --> | ||
| <!-- Replace the content tag with appropriate information --> | ||
| <meta name="description" content="Road generation meets AI"> | ||
| <meta property="og:title" content="Evolution Guided Generative Flow Networks"/> | ||
| <meta property="og:description" content="Civil Engineering meets AI"/> | ||
| <meta property="og:url" content="https:zarifikram.github.io/gfn-roundabout"/> | ||
| <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X630--> | ||
| <meta property="og:image" content="static/images/image1.png" /> | ||
| <meta property="og:image:width" content="1200"/> | ||
| <meta property="og:image:height" content="630"/> | ||
|
|
||
|
|
||
| <meta name="twitter:title" content="Evolution Guided Generative Flow Networks"> | ||
| <meta name="twitter:description" content="Evolutionary algorithm, meet GFlowNets"> | ||
| <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X600--> | ||
| <meta name="twitter:image" content="static/images/your_twitter_banner_image.png"> | ||
| <meta name="twitter:card" content="summary_large_image"> | ||
| <!-- Keywords for your paper to be indexed by--> | ||
| <meta name="keywords" content="Probabilistic generation gflownet roundabout gfn zarif ikram mit mila"> | ||
| <meta name="viewport" content="width=device-width, initial-scale=1"> | ||
|
|
||
|
|
||
| <title>Evolution Guided Generative Flow Networks</title> | ||
| <link rel="icon" type="image/x-icon" href="static/images/favicon.ico"> | ||
| <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" | ||
| rel="stylesheet"> | ||
|
|
||
| <link rel="stylesheet" href="static/css/bulma.min.css"> | ||
| <link rel="stylesheet" href="static/css/bulma-carousel.min.css"> | ||
| <link rel="stylesheet" href="static/css/bulma-slider.min.css"> | ||
| <link rel="stylesheet" href="static/css/fontawesome.all.min.css"> | ||
| <link rel="stylesheet" | ||
| href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css"> | ||
| <link rel="stylesheet" href="static/css/index.css"> | ||
|
|
||
| <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script> | ||
| <script src="https://documentcloud.adobe.com/view-sdk/main.js"></script> | ||
| <script defer src="static/js/fontawesome.all.min.js"></script> | ||
| <script src="static/js/bulma-carousel.min.js"></script> | ||
| <script src="static/js/bulma-slider.min.js"></script> | ||
| <script src="static/js/index.js"></script> | ||
| </head> | ||
| <body> | ||
|
|
||
|
|
||
| <section class="hero"> | ||
| <div class="hero-body"> | ||
| <div class="container is-max-desktop"> | ||
| <div class="columns is-centered"> | ||
| <div class="column has-text-centered"> | ||
| <h1 class="title is-1 publication-title">Evolution Guided Generative Flow Networks</h1> | ||
| <div class="is-size-5 publication-authors"> | ||
| <!-- Paper authors --> | ||
| <span class="author-block"> | ||
| <a href="https://zarifikram.github.io" target="_blank">Zarif Ikram</a><sup>1</sup>,</span> | ||
| <span class="author-block"> | ||
| <a href="http://ling-pan.github.io" target="_blank">Ling Pan</a><sup>2</sup>,</span> | ||
| <span class="author-block"> | ||
| <a href="http://dianboliu.github.io" target="_blank">Dianbo Liu</a><sup>3</sup> | ||
| </span> | ||
| </div> | ||
|
|
||
| <div class="is-size-5 publication-authors"> | ||
| <span class="author-block"><sup>1</sup>Department of CSE, BUET, Bangladesh <sup>2</sup>The Hong Kong University of Science and Technology, Hong Kong <sup>3</sup>National University of Singapore, Singapore<br><a href="https://www.gembio.ai"> 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design</a></span> | ||
| <!-- <span class="eql-cntrb"><small><br><sup>*</sup>Indicates Equal Contribution</small></span> --> | ||
| </div> | ||
|
|
||
| <div class="column has-text-centered"> | ||
| <div class="publication-links"> | ||
| <!-- Arxiv PDF link --> | ||
| <span class="link-block"> | ||
| <a href="https://arxiv.org/pdf/2402.02186.pdf" target="_blank" | ||
| class="external-link button is-normal is-rounded is-dark"> | ||
| <span class="icon"> | ||
| <i class="fas fa-file-pdf"></i> | ||
| </span> | ||
| <span>Paper</span> | ||
| </a> | ||
| </span> | ||
|
|
||
| <!-- Supplementary PDF link | ||
| <span class="link-block"> | ||
| <a href="static/pdfs/supplementary_material.pdf" target="_blank" | ||
| class="external-link button is-normal is-rounded is-dark"> | ||
| <span class="icon"> | ||
| <i class="fas fa-file-pdf"></i> | ||
| </span> | ||
| <span>Supplementary</span> | ||
| </a> | ||
| </span> --> | ||
|
|
||
| <!-- Github link --> | ||
| <span class="link-block"> | ||
| <a href="https://github.com/zarifikram/egfn" target="_blank" | ||
| class="external-link button is-normal is-rounded is-dark"> | ||
| <span class="icon"> | ||
| <i class="fab fa-github"></i> | ||
| </span> | ||
| <span>Code</span> | ||
| </a> | ||
| </span> | ||
|
|
||
| <!-- ArXiv abstract Link --> | ||
| <span class="link-block"> | ||
| <a href="https://arxiv.org/abs/2402.02186" target="_blank" | ||
| class="external-link button is-normal is-rounded is-dark"> | ||
| <span class="icon"> | ||
| <i class="ai ai-arxiv"></i> | ||
| </span> | ||
| <span>arXiv</span> | ||
| </a> | ||
| </span> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </section> | ||
|
|
||
|
|
||
| <!-- Teaser video--> | ||
|
|
||
| <!-- End teaser video --> | ||
|
|
||
| <!-- Paper abstract --> | ||
| <section class="section hero is-light"> | ||
| <div class="container is-max-desktop"> | ||
| <div class="columns is-centered has-text-centered"> | ||
| <div class="column is-four-fifths"> | ||
| <h2 class="title is-3">Abstract</h2> | ||
| <div class="content has-text-justified"> | ||
| <p> | ||
| Generative Flow Networks (GFlowNets) are a family of probabilistic generative models that learn to sample compositional objects proportional to their rewards. One big challenge of GFlowNets is training them effectively when dealing with long time horizons and sparse rewards. To address this, we propose Evolution guided generative flow networks (EGFN), a simple but powerful augmentation to the GFlowNets training using Evolutionary algorithms (EA). Our method can work on top of any GFlowNets training objective, by training a set of agent parameters using EA, storing the resulting trajectories in the prioritized replay buffer, and training the GFlowNets agent using the stored trajectories. We present a thorough investigation over a wide range of toy and real-world benchmark tasks showing the effectiveness of our method in handling long trajectories and sparse rewards. | ||
| </p> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </section> | ||
| <!-- End paper abstract --> | ||
|
|
||
|
|
||
| <!-- Image carousel --> | ||
| <section class="hero is-small"> | ||
| <div class="hero-body"> | ||
| <div class="container"> | ||
| <div id="results-carousel" class="carousel results-carousel"> | ||
| <div class="item"> | ||
| <!-- Your image here --> | ||
| <img src="static/images/image1.png" alt="MY ALT TEXT"/> | ||
| <h2 class="subtitle has-text-centered"> | ||
| <!-- Given incident road configurations, we generate a roundabout by inferring the circular structure from the incident roads. A valid solution is a roundabout that connects all the incident roads with any overlap between the connecting roads. --> | ||
| </h2> | ||
| </div> | ||
| <div class="item"> | ||
| <!-- Your image here --> | ||
| <img src="static/images/image2.png" alt="MY ALT TEXT" style="width: 50%;"/> | ||
| <h2 class="subtitle has-text-centered"> | ||
| <!-- MDP design for incident road configuration generation. Number on dark filled circles on the dotted circle represent the endpoints of circle road segments. Small filled circle with arrow represent the road definition where direction of the arrow represent the heading of the initial road. --> | ||
| </h2> | ||
| </div> | ||
| <div class="item"> | ||
| <!-- Your image here --> | ||
| <img src="static/images/image3.png" alt="MY ALT TEXT"/> | ||
| <h2 class="subtitle has-text-centered"> | ||
| <!-- To reduce time complexity of validating a roundabout after construction, we propose a proxy reward that estimates the validation using straight line intersection. Left: Geometry of a generated roundabout. Right: Geometry generated by the proxy reward function. --> | ||
| </h2> | ||
| </div> | ||
| <div class="item"> | ||
| <!-- Your image here --> | ||
| <img src="static/images/image4.png" alt="MY ALT TEXT"/> | ||
| <h2 class="subtitle has-text-centered"> | ||
| <!-- Ablation study on GFlowNet training. We see the number of modes sampled increases with hidden dim and base value. --> | ||
| </h2> | ||
| </div> | ||
| <div class="item"> | ||
| <!-- Your image here --> | ||
| <img src="static/images/image5.png" alt="MY ALT TEXT"/> | ||
| <h2 class="subtitle has-text-centered"> | ||
| <!-- Ablation study on GFlowNet training. We see the number of modes sampled increases with hidden dim and base value. --> | ||
| </h2> | ||
| </div> | ||
| <div class="item"> | ||
| <!-- Your image here --> | ||
| <img src="static/images/image6.png" alt="MY ALT TEXT"/> | ||
| <h2 class="subtitle has-text-centered"> | ||
| <!-- Ablation study on GFlowNet training. We see the number of modes sampled increases with hidden dim and base value. --> | ||
| </h2> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </section> | ||
| <!-- End image carousel --> | ||
|
|
||
|
|
||
|
|
||
|
|
||
| <!-- Youtube video --> | ||
|
|
||
| <!-- End youtube video --> | ||
|
|
||
|
|
||
| <!-- Video carousel --> | ||
|
|
||
| <!-- End video carousel --> | ||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
| <!-- Paper poster --> | ||
| <!-- <section class="hero is-small is-light"> | ||
| <div class="hero-body"> | ||
| <div class="container"> | ||
| <h2 class="title">Poster</h2> | ||
| <iframe src="static/pdfs/GFN-Roundabout_Ikram2023.pdf" width="100%" height="550"> | ||
| </iframe> | ||
| </div> | ||
| </div> | ||
| </section> --> | ||
| <!--End paper poster --> | ||
|
|
||
|
|
||
| <!--BibTex citation --> | ||
| <section class="section" id="BibTeX"> | ||
| <div class="container is-max-desktop content"> | ||
| <h2 class="title">BibTeX</h2> | ||
| <pre><code>@inproceedings{ | ||
| anonymous2024evolution, | ||
| title={Evolution Guided Generative Flow Networks}, | ||
| author={Anonymous}, | ||
| booktitle={ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design}, | ||
| year={2024}, | ||
| url={https://openreview.net/forum?id=9Re0rOaYAH} | ||
| }</code></pre> | ||
| </div> | ||
| </section> | ||
| <!--End BibTex citation --> | ||
|
|
||
|
|
||
| <!-- <footer class="footer"> | ||
| <div class="container"> | ||
| <div class="columns is-centered"> | ||
| <div class="column is-8"> | ||
| <div class="content"> | ||
| <p> | ||
| This page was built using the <a href="https://github.com/eliahuhorwitz/Academic-project-page-template" target="_blank">Academic Project Page Template</a> which was adopted from the <a href="https://nerfies.github.io" target="_blank">Nerfies</a> project page. | ||
| You are free to borrow the of this website, we just ask that you link back to this page in the footer. <br> This website is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/" target="_blank">Creative | ||
| Commons Attribution-ShareAlike 4.0 International License</a>. | ||
| </p> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </div> | ||
| </footer> --> | ||
|
|
||
| <!-- Statcounter tracking code --> | ||
|
|
||
| <!-- You can add a tracker to track page visits by creating an account at statcounter.com --> | ||
|
|
||
| <!-- End of Statcounter Code --> | ||
|
|
||
| </body> | ||
| </html> |
Binary file not shown.
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
Oops, something went wrong.