{"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/valid-conformal-prediction-for-dynamic-gnns","title":"Valid Conformal Prediction for Dynamic GNNs","arxiv_id":"2405.19230","date":"2024-05-29","proceeding":null,"authors":["Ed Davis","Ian Gallagher","Daniel John Lawson","Patrick Rubin-Delanchy"],"abstract":"Dynamic graphs provide a flexible data abstraction for modelling many sorts of real-world systems, such as transport, trade, and social networks. Graph neural networks (GNNs) are powerful tools allowing for different kinds of prediction and inference on these systems, but getting a handle on uncertainty, especially in dynamic settings, is a challenging problem. In this work we propose to use a dynamic graph representation known in the tensor literature as the unfolding, to achieve valid prediction sets via conformal prediction. This representation, a simple graph, can be input to any standard GNN and does not require any modification to existing GNN architectures or conformal prediction routines. One of our key contributions is a careful mathematical consideration of the different inference scenarios which can arise in a dynamic graph modelling context. For a range of practically relevant cases, we obtain valid prediction sets with almost no assumptions, even dispensing with exchangeability. In a more challenging scenario, which we call the semi-inductive regime, we achieve valid prediction under stronger assumptions, akin to stationarity. We provide real data examples demonstrating validity, showing improved accuracy over baselines, and sign-posting different failure modes which can occur when those assumptions are violated.","url_abs":"https://arxiv.org/abs/2405.19230v2","url_pdf":"https://arxiv.org/pdf/2405.19230v2.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":"valid-conformal-prediction-for-dynamic-gnns","repo_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conformal-prediction","task_name":"Conformal Prediction"},{"task_slug":"dynamic-graph-embedding","task_name":"Dynamic graph embedding"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.19230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19230"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/edwarddavis1/valid_conformal_for_dynamic_gnn","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":6},"by_repo_kind":{"official":{"samples":12,"ran":6,"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":12,"samples":[{"code_sha256_prefix":"efe10fdcadd227a7","entry":"general_unfolded_matrix","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"gnn_embedding_functions.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/gnn_embedding_functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efe10fdcadd227a7"}},{"code_sha256_prefix":"3a54f0d0cbe25a4f","entry":"make_iid","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"experiment_setup.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/experiment_setup.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a54f0d0cbe25a4f"}},{"code_sha256_prefix":"a09f7978c4c75b34","entry":"mask_split","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"Conformal_GNN_SBM_Experiments.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/Conformal_GNN_SBM_Experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a09f7978c4c75b34"}},{"code_sha256_prefix":"ab336c6481f4ba46","entry":"single_spectral","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"embedding_functions.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/embedding_functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab336c6481f4ba46"}},{"code_sha256_prefix":"13f8e4e77a5b5ded","entry":"valid","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"Conformal_GNN_Flight_Experiments.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/Conformal_GNN_Flight_Experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13f8e4e77a5b5ded"}},{"code_sha256_prefix":"25d3ac5915c98422","entry":"valid","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"Conformal_GNN_Global_Experiments.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/Conformal_GNN_Global_Experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25d3ac5915c98422"}},{"code_sha256_prefix":"37ce25b91d8510da","entry":"SSE","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"embedding_functions.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/embedding_functions.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":"37ce25b91d8510da"}},{"code_sha256_prefix":"df3b2dc44d3f10da","entry":"UGCN","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"gnn_embedding_functions.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/gnn_embedding_functions.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":"df3b2dc44d3f10da"}},{"code_sha256_prefix":"a70bfa5731e7a52c","entry":"block_GCN","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"gnn_embedding_functions.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/gnn_embedding_functions.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":"a70bfa5731e7a52c"}},{"code_sha256_prefix":"5364c61f6707b196","entry":"procrust_align","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"embedding_functions.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/embedding_functions.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":"5364c61f6707b196"}},{"code_sha256_prefix":"d7aa3608877162ac","entry":"train","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"Conformal_GNN_Flight_Experiments.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/Conformal_GNN_Flight_Experiments.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":"d7aa3608877162ac"}},{"code_sha256_prefix":"08ae9e2d51fdc4c0","entry":"train","repo":"edwarddavis1/valid_conformal_for_dynamic_gnn","repo_kind":"official","path":"Conformal_GNN_Global_Experiments.py","file_url":"https://github.com/edwarddavis1/valid_conformal_for_dynamic_gnn/blob/HEAD/Conformal_GNN_Global_Experiments.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":"08ae9e2d51fdc4c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}