{"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/snowflake-scaling-gnns-to-high-dimensional","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","arxiv_id":"2103.01009","date":"2021-03-01","proceeding":"NeurIPS 2021 12","authors":["Charlie Blake","Vitaly Kurin","Maximilian Igl","Shimon Whiteson"],"abstract":"Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron (MLP), with superior transfer and multi-task performance (Wang et al., 2018; Huang et al., 2020). Results have so far been limited to training on small agents, with the performance of GNNs deteriorating rapidly as the number of sensors and actuators grows. A key motivation for the use of GNNs in the supervised learning setting is their applicability to large graphs, but this benefit has not yet been realised for locomotion control. We identify the weakness with a common GNN architecture that causes this poor scaling: overfitting in the MLPs within the network that encode, decode, and propagate messages. To combat this, we introduce Snowflake, a GNN training method for high-dimensional continuous control that freezes parameters in parts of the network that suffer from overfitting. Snowflake significantly boosts the performance of GNNs for locomotion control on large agents, now matching the performance of MLPs, and with superior transfer properties.","url_abs":"https://arxiv.org/abs/2103.01009v3","url_pdf":"https://arxiv.org/pdf/2103.01009v3.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":"snowflake-scaling-gnns-to-high-dimensional","repo_url":"https://github.com/thecharlieblake/snowflake","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2103.01009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01009"}},"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":"deterministic:regex_extraction","url":"https://github.com/openai/gym","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/thecharlieblake/snowflake","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/WilsonWangTHU/NerveNet","reach":{"status":"unanswered"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"c672573da76b475d","entry":"GatedGraphNetwork","repo":"thecharlieblake/snowflake","repo_kind":"official","path":"network/gated_graph_network.py","file_url":"https://github.com/thecharlieblake/snowflake/blob/HEAD/network/gated_graph_network.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":"c672573da76b475d"}},{"code_sha256_prefix":"29990aeb1de07ce8","entry":"Network","repo":"thecharlieblake/snowflake","repo_kind":"official","path":"network/gated_graph_network.py","file_url":"https://github.com/thecharlieblake/snowflake/blob/HEAD/network/gated_graph_network.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":"29990aeb1de07ce8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}