{"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/implicit-graph-neural-diffusion-based-on","title":"Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing","arxiv_id":"2308.03306","date":"2023-08-07","proceeding":null,"authors":["Guoji Fu","Mohammed Haroon Dupty","Yanfei Dong","Lee Wee Sun"],"abstract":"Implicit Graph Neural Networks (GNNs) have achieved significant success in addressing graph learning problems recently. However, poorly designed implicit GNN layers may have limited adaptability to learn graph metrics, experience over-smoothing issues, or exhibit suboptimal convergence and generalization properties, potentially hindering their practical performance. To tackle these issues, we introduce a geometric framework for designing implicit graph diffusion layers based on a parameterized graph Laplacian operator. Our framework allows learning the metrics of vertex and edge spaces, as well as the graph diffusion strength from data. We show how implicit GNN layers can be viewed as the fixed-point equation of a Dirichlet energy minimization problem and give conditions under which it may suffer from over-smoothing during training (OST) and inference (OSI). We further propose a new implicit GNN model to avoid OST and OSI. We establish that with an appropriately chosen hyperparameter greater than the largest eigenvalue of the parameterized graph Laplacian, DIGNN guarantees a unique equilibrium, quick convergence, and strong generalization bounds. Our models demonstrate better performance than most implicit and explicit GNN baselines on benchmark datasets for both node and graph classification tasks.","url_abs":"https://arxiv.org/abs/2308.03306v2","url_pdf":"https://arxiv.org/pdf/2308.03306v2.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":"implicit-graph-neural-diffusion-based-on","repo_url":"https://github.com/guoji-fu/dignn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.03306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03306"}},"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/guoji-fu/dignn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11,"ran_honours":1},"by_repo_kind":{"official":{"samples":12,"ran":12,"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":0,"samples":[{"code_sha256_prefix":"22e59b82a78a0990","entry":"build_model","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/main_ppi.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/main_ppi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22e59b82a78a0990"}},{"code_sha256_prefix":"2e526670952f0e17","entry":"compute_exact_uT","repo":"guoji-fu/dignn","repo_kind":"official","path":"graphclassification/src/solvers.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/graphclassification/src/solvers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e526670952f0e17"}},{"code_sha256_prefix":"e4a2760099cc5a69","entry":"fwd_solver","repo":"guoji-fu/dignn","repo_kind":"official","path":"graphclassification/src/solvers.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/graphclassification/src/solvers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a2760099cc5a69"}},{"code_sha256_prefix":"0c20d2ddb8b92d0c","entry":"g","repo":"guoji-fu/dignn","repo_kind":"official","path":"graphclassification/src/functions.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/graphclassification/src/functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c20d2ddb8b92d0c"}},{"code_sha256_prefix":"66811722ba344c40","entry":"g","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/baselines.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/baselines.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66811722ba344c40"}},{"code_sha256_prefix":"79b9eb50dc9aee27","entry":"get_G","repo":"guoji-fu/dignn","repo_kind":"official","path":"graphclassification/src/functions.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/graphclassification/src/functions.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79b9eb50dc9aee27"}},{"code_sha256_prefix":"fd793363ac8ba6ea","entry":"new_solver","repo":"guoji-fu/dignn","repo_kind":"official","path":"graphclassification/src/solvers.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/graphclassification/src/solvers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd793363ac8ba6ea"}},{"code_sha256_prefix":"259d4544dc760378","entry":"one_hot","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/linkx_dataset.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/linkx_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"259d4544dc760378"}},{"code_sha256_prefix":"c1d6392f89c5e495","entry":"parse_index_file","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/data.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/data.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1d6392f89c5e495"}},{"code_sha256_prefix":"923136b4a244566b","entry":"preprocess_features","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/data.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"923136b4a244566b"}},{"code_sha256_prefix":"cf642365a4d2fd72","entry":"test","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/main_ppi.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/main_ppi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf642365a4d2fd72"}},{"code_sha256_prefix":"bddc79fec76e9fec","entry":"train","repo":"guoji-fu/dignn","repo_kind":"official","path":"nodeclassification/main_ppi.py","file_url":"https://github.com/guoji-fu/dignn/blob/HEAD/nodeclassification/main_ppi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bddc79fec76e9fec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}