{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/da-moe-addressing-depth-sensitivity-in-graph","title":"DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts","arxiv_id":"2411.03025","date":"2024-11-05","proceeding":null,"authors":["Zelin Yao","Chuang Liu","Xianke Meng","Yibing Zhan","Jia Wu","Shirui Pan","Wenbin Hu"],"abstract":"Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. In real-world scenarios, graph data within the same dataset can vary significantly in scale. This variability leads to depth-sensitivity, where the optimal depth of GNN layers depends on the scale of the graph data. Empirically, fewer layers are sufficient for message passing in smaller graphs, while larger graphs typically require deeper networks to capture long-range dependencies and global features. However, existing methods generally use a fixed number of GNN layers to generate representations for all graphs, overlooking the depth-sensitivity issue in graph structure data. To address this challenge, we propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN backbone: \\textbf{1)} DA-MoE employs different GNN layers, each considered an expert with its own parameters. Such a design allows the model to flexibly aggregate information at different scales, effectively addressing the depth-sensitivity issue in graph data. \\textbf{2)} DA-MoE utilizes GNN to capture the structural information instead of the linear projections in the gating network. Thus, the gating network enables the model to capture complex patterns and dependencies within the data. By leveraging these improvements, each expert in DA-MoE specifically learns distinct graph patterns at different scales. Furthermore, comprehensive experiments on the TU dataset and open graph benchmark (OGB) have shown that DA-MoE consistently surpasses existing baselines on various tasks, including graph, node, and link-level analyses. The code are available at \\url{https://github.com/Celin-Yao/DA-MoE}.","url_abs":"https://arxiv.org/abs/2411.03025v1","url_pdf":"https://arxiv.org/pdf/2411.03025v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"da-moe-addressing-depth-sensitivity-in-graph","repo_url":"https://github.com/celin-yao/da-moe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.03025","atlas_url":"https://app.syntology.ai/?focus=2411.03025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03025"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/celin-yao/da-moe","reach":null}],"summary":{"ran_honours":3,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"8e6629dff4ea0a71","entry":"test","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8e6629dff4ea0a71"}},{"code_sha256_prefix":"df2960ace0a8870f","entry":"test","repo":"celin-yao/da-moe","repo_kind":"official","path":"link_prediction/main_link_ddi.py","file_url":"https://github.com/celin-yao/da-moe/blob/HEAD/link_prediction/main_link_ddi.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df2960ace0a8870f"}},{"code_sha256_prefix":"9839952e23a76564","entry":"train","repo":"celin-yao/da-moe","repo_kind":"official","path":"graph_classification/train/main_graph.py","file_url":"https://github.com/celin-yao/da-moe/blob/HEAD/graph_classification/train/main_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9839952e23a76564"}},{"code_sha256_prefix":"3bbf2963d8be10dd","entry":"train","repo":"celin-yao/da-moe","repo_kind":"official","path":"node_classification/main_node_arxiv.py","file_url":"https://github.com/celin-yao/da-moe/blob/HEAD/node_classification/main_node_arxiv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3bbf2963d8be10dd"}},{"code_sha256_prefix":"948172fd0a8279b0","entry":"train_moe","repo":"celin-yao/da-moe","repo_kind":"official","path":"graph_classification/train/main_graph.py","file_url":"https://github.com/celin-yao/da-moe/blob/HEAD/graph_classification/train/main_graph.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"948172fd0a8279b0"}},{"code_sha256_prefix":"2bd54b1565228864","entry":"test","repo":"celin-yao/da-moe","repo_kind":"official","path":"graph_classification/train/main_graph.py","file_url":"https://github.com/celin-yao/da-moe/blob/HEAD/graph_classification/train/main_graph.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bd54b1565228864"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}