{"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/on-the-unreasonable-effectiveness-of-feature-1","title":"On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features","arxiv_id":"2111.12128","date":"2021-11-23","proceeding":null,"authors":["Emanuele Rossi","Henry Kenlay","Maria I. Gorinova","Benjamin Paul Chamberlain","Xiaowen Dong","Michael Bronstein"],"abstract":"While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in social networks, age and gender are available only for a small subset of users. We present a general approach for handling missing features in graph machine learning applications that is based on minimization of the Dirichlet energy and leads to a diffusion-type differential equation on the graph. The discretization of this equation produces a simple, fast and scalable algorithm which we call Feature Propagation. We experimentally show that the proposed approach outperforms previous methods on seven common node-classification benchmarks and can withstand surprisingly high rates of missing features: on average we observe only around 4% relative accuracy drop when 99% of the features are missing. Moreover, it takes only 10 seconds to run on a graph with $\\sim$2.5M nodes and $\\sim$123M edges on a single GPU.","url_abs":"https://arxiv.org/abs/2111.12128v3","url_pdf":"https://arxiv.org/pdf/2111.12128v3.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":"on-the-unreasonable-effectiveness-of-feature-1","repo_url":"https://github.com/twitter-research/feature-propagation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.12128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12128"}},"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/twitter-research/feature-propagation","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"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":"cc49cd8a589e02de","entry":"ex_relu","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/baselines/gcn_mf.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/baselines/gcn_mf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc49cd8a589e02de"}},{"code_sha256_prefix":"c68140584cc0e991","entry":"get_component","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c68140584cc0e991"}},{"code_sha256_prefix":"338d87d585e0b11d","entry":"get_conv","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"338d87d585e0b11d"}},{"code_sha256_prefix":"b36878b25e3455a3","entry":"get_largest_connected_component","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b36878b25e3455a3"}},{"code_sha256_prefix":"12003dcf4549f5a3","entry":"get_mask","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12003dcf4549f5a3"}},{"code_sha256_prefix":"bdff77b67175af09","entry":"get_missing_feature_mask","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bdff77b67175af09"}},{"code_sha256_prefix":"09a790aab330a10e","entry":"inference_full_batch","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/evaluation.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"09a790aab330a10e"}},{"code_sha256_prefix":"17f844b866904bc9","entry":"inference_sampled","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/evaluation.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17f844b866904bc9"}},{"code_sha256_prefix":"56a5ef8b43881fac","entry":"init_gmm","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/baselines/gcn_mf.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/baselines/gcn_mf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56a5ef8b43881fac"}},{"code_sha256_prefix":"9e01cbb3f563b6df","entry":"keep_only_largest_connected_component","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e01cbb3f563b6df"}},{"code_sha256_prefix":"b8ff0add0a440e77","entry":"mean_filling","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/filling_strategies.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/filling_strategies.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b8ff0add0a440e77"}},{"code_sha256_prefix":"6161e8125aef4044","entry":"random_filling","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/filling_strategies.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/filling_strategies.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6161e8125aef4044"}},{"code_sha256_prefix":"917430c937090e71","entry":"test","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/evaluation.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"917430c937090e71"}},{"code_sha256_prefix":"603473b3dc2838d0","entry":"zero_filling","repo":"twitter-research/feature-propagation","repo_kind":"official","path":"src/filling_strategies.py","file_url":"https://github.com/twitter-research/feature-propagation/blob/HEAD/src/filling_strategies.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"603473b3dc2838d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}