{"id":31517696,"url":"https://github.com/imoonlab/lhdformer","last_synced_at":"2025-10-03T07:38:02.931Z","repository":{"id":315426726,"uuid":"1059442932","full_name":"iMoonLab/LHDFormer","owner":"iMoonLab","description":null,"archived":false,"fork":false,"pushed_at":"2025-09-18T13:25:13.000Z","size":302,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-18T15:50:33.599Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/iMoonLab.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-18T13:00:32.000Z","updated_at":"2025-09-18T13:25:46.000Z","dependencies_parsed_at":"2025-09-18T16:03:37.665Z","dependency_job_id":null,"html_url":"https://github.com/iMoonLab/LHDFormer","commit_stats":null,"previous_names":["imoonlab/lhdformer"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/iMoonLab/LHDFormer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FLHDFormer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FLHDFormer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FLHDFormer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FLHDFormer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iMoonLab","download_url":"https://codeload.github.com/iMoonLab/LHDFormer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FLHDFormer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278130069,"owners_count":25934860,"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","status":"online","status_checked_at":"2025-10-03T02:00:06.070Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2025-10-03T07:38:00.884Z","updated_at":"2025-10-03T07:38:02.923Z","avatar_url":"https://github.com/iMoonLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ch2\u003eAdaptive Embedding for Long-Range High-Order Dependencies via Time-Varying Transformer on fMRI\u003c/h2\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cb\u003eRundong Xue, Xiangmin Han\u003csup\u003e*\u003c/sup\u003e, Hao Hu, Zeyu Zhang, Shaoyi Du\u003csup\u003e*\u003c/sup\u003e, Yue Gao\u003c/b\u003e\n\u003c/p\u003e\n\nAccepted by _**MICCAI 2025**_\n\n[[Paper]](https://papers.miccai.org/miccai-2025/paper/0949_paper.pdf)\n\n\u003c/div\u003e\n\n## Overview\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"figures/pipeline.png\"\u003e\n\u003c/div\u003e\n\n\n**Figure 1. The framework of the proposed LHDFormer.**\n\n\n**_Abstract -_** Dynamic functional brain network analysis using rs-fMRI has emerged as a powerful approach to understanding brain disorders. However, current methods predominantly focus on pairwise brain region interactions, neglecting critical high-order dependencies and time-varying communication mechanisms. To address these limitations, we propose the Long-Range High-Order Dependency Transformer (LHDFormer), a neurophysiologically-inspired framework that integrates multiscale long-range dependencies with time-varying connectivity patterns. Specifically, we present a biased random walk sampling strategy with NeuroWalk kernel-guided transfer probabilities that dynamically simulate multi-step information loss through a $k$-walk neuroadaptive factor, modeling brain neurobiological principles such as distance-dependent information loss and state-dependent pathway modulation. This enables the adaptive capture of the multi-scale short-range couplings and long-range high-order dependencies corresponding to different steps across evolving connectivity patterns. Complementing this, the time-varying transformer co-embeds local spatial configurations via topology-aware attention and global temporal dynamics through cross-window token guidance, overcoming the single-domain bias of conventional graph/transformer methods. Extensive experiments on ABIDE and ADNI datasets demonstrate that LHDFormer outperforms state-of-the-art methods in brain disease diagnosis. Crucially, the model identifies interpretable high-order connectivity signatures, revealing disrupted long-range integration patterns in patients that align with known neuropathological mechanisms.\n\n## Dependencies\n\n  - python=3.9\n  - cudatoolkit=11.3\n  - torchvision=0.13.1\n  - pytorch=1.12.1\n  - torchaudio=0.12.1\n  - wandb=0.13.1\n  - scikit-learn=1.1.1\n  - pandas=1.4.3\n  - hydra-core=1.2.0\n\n## Get Started\n### 1. Data Preparation\nDownload the ABIDE dataset from [here](https://drive.google.com/file/d/14UGsikYH_SQ-d_GvY2Um2oEHw3WNxDY3/view?usp=sharing).\n\n### 2. Usage\nRun the following command to train the model.\n```bash\nsh main.sh\n```\n\n## Cite our work\n```bibtex\n@inproceedings{xue2025adaptive,\n  title={Adaptive Embedding for Long-Range High-Order Dependencies via Time-Varying Transformer on fMRI},\n  author={Xue, Rundong and Han, Xiangmin and Hu, Hao and Zhang, Zeyu and Du, Shaoyi and Gao, Yue},\n  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},\n  pages={46--55},\n  year={2025},\n  organization={Springer}\n}\n```\n\n## License\nThe source code is free for research and educational use only. Any commercial use should get formal permission first.\n\nThis repo benefits from [BNT](https://github.com/Wayfear/BrainNetworkTransformer) and [ALTER](https://github.com/yushuowiki/ALTER). Thanks for their wonderful works.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimoonlab%2Flhdformer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimoonlab%2Flhdformer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimoonlab%2Flhdformer/lists"}