{"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/distillating-knowledge-from-graph","title":"Distilling Knowledge from Graph Convolutional Networks","arxiv_id":"2003.10477","date":"2020-03-23","proceeding":"CVPR 2020 6","authors":["Yiding Yang","Jiayan Qiu","Mingli Song","DaCheng Tao","Xinchao Wang"],"abstract":"Existing knowledge distillation methods focus on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, and have largely overlooked graph convolutional networks (GCN) that handle non-grid data. In this paper, we propose to our best knowledge the first dedicated approach to distilling knowledge from a pre-trained GCN model. To enable the knowledge transfer from the teacher GCN to the student, we propose a local structure preserving module that explicitly accounts for the topological semantics of the teacher. In this module, the local structure information from both the teacher and the student are extracted as distributions, and hence minimizing the distance between these distributions enables topology-aware knowledge transfer from the teacher, yielding a compact yet high-performance student model. Moreover, the proposed approach is readily extendable to dynamic graph models, where the input graphs for the teacher and the student may differ. We evaluate the proposed method on two different datasets using GCN models of different architectures, and demonstrate that our method achieves the state-of-the-art knowledge distillation performance for GCN models. Code is publicly available at https://github.com/ihollywhy/DistillGCN.PyTorch.","url_abs":"https://arxiv.org/abs/2003.10477v4","url_pdf":"https://arxiv.org/pdf/2003.10477v4.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":"distillating-knowledge-from-graph","repo_url":"https://github.com/ihollywhy/DistillGCN.PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"graph-convolutional-networks","method_name":"Graph Convolutional Networks"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.10477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10477"}},"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/ihollywhy/DistillGCN.PyTorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"adade861c08470cb","entry":"evaluate","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adade861c08470cb"}},{"code_sha256_prefix":"74ef452085c20e34","entry":"generate_label","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74ef452085c20e34"}},{"code_sha256_prefix":"f529fb33becac8f2","entry":"get_discriminator","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"discriminator_model.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/discriminator_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f529fb33becac8f2"}},{"code_sha256_prefix":"92eacea3540f32fa","entry":"get_transformer_model","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"atransfor_model.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/atransfor_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92eacea3540f32fa"}},{"code_sha256_prefix":"c2088eb26db4bc18","entry":"loss_fn_kd","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"auxilary_loss.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/auxilary_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2088eb26db4bc18"}},{"code_sha256_prefix":"eaa7e1b54e1cc490","entry":"parameters","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"plot_utils.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/plot_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eaa7e1b54e1cc490"}},{"code_sha256_prefix":"37a7a4358779ae46","entry":"test_model","repo":"ihollywhy/DistillGCN.PyTorch","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ihollywhy/DistillGCN.PyTorch/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37a7a4358779ae46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}