{"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/spectral-temporal-graph-neural-network-for-1","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","arxiv_id":"2103.07719","date":"2021-03-13","proceeding":"NeurIPS 2020 12","authors":["Defu Cao","Yujing Wang","Juanyong Duan","Ce Zhang","Xia Zhu","Conguri Huang","Yunhai Tong","Bixiong Xu","Jing Bai","Jie Tong","Qi Zhang"],"abstract":"Multivariate time-series forecasting plays a crucial role in many real-world applications. It is a challenging problem as one needs to consider both intra-series temporal correlations and inter-series correlations simultaneously. Recently, there have been multiple works trying to capture both correlations, but most, if not all of them only capture temporal correlations in the time domain and resort to pre-defined priors as inter-series relationships. In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting. StemGNN captures inter-series correlations and temporal dependencies \\textit{jointly} in the \\textit{spectral domain}. It combines Graph Fourier Transform (GFT) which models inter-series correlations and Discrete Fourier Transform (DFT) which models temporal dependencies in an end-to-end framework. After passing through GFT and DFT, the spectral representations hold clear patterns and can be predicted effectively by convolution and sequential learning modules. Moreover, StemGNN learns inter-series correlations automatically from the data without using pre-defined priors. We conduct extensive experiments on ten real-world datasets to demonstrate the effectiveness of StemGNN. Code is available at https://github.com/microsoft/StemGNN/","url_abs":"https://arxiv.org/abs/2103.07719v1","url_pdf":"https://arxiv.org/pdf/2103.07719v1.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":"spectral-temporal-graph-neural-network-for-1","repo_url":"https://github.com/WenjieDu/PyPOTS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"spectral-temporal-graph-neural-network-for-1","repo_url":"https://github.com/microsoft/StemGNN","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"spectral-temporal-graph-neural-network-for-1","repo_url":"https://github.com/abdulmajid-murad/deep_probabilistic_forecast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"multivariate-time-series-forecasting","task_name":"Multivariate Time Series Forecasting"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-expy-tky-1","task":"Traffic Prediction","dataset":"EXPY-TKY","model":"StemGNN","rank_in_archive_order":8,"of":8,"metrics":{"1 step MAE":"6.08","3 step MAE":"6.85","6 step MAE":"7.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.07719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07719"}},"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/microsoft/StemGNN","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/farizrahman4u/seq2seq","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/z331565360/State-Frequency-Memory-stock-prediction","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/philipperemy/n-beats","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/fbadine/LSTNet","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/liyaguang/DCRNN","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/VeritasYin/STGCN_IJCAI-18","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/locuslab/TCN","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nnzhan/Graph-WaveNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abdulmajid-murad/deep_probabilistic_forecast","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WenjieDu/PyPOTS","reach":null}],"summary":{"ran":2,"unverified":11},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"named_in_paper":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":2,"ran":1,"repositories":1},"found_in_text":{"samples":6,"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":"b2565ba72dc20edd","entry":"GLU","repo":"abdulmajid-murad/deep_probabilistic_forecast","repo_kind":"listed","path":"probabilistic_forecast/utils/gnn_utils.py","file_url":"https://github.com/abdulmajid-murad/deep_probabilistic_forecast/blob/HEAD/probabilistic_forecast/utils/gnn_utils.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":"b2565ba72dc20edd"}},{"code_sha256_prefix":"95172885d816bacd","entry":"GLU","repo":"WenjieDu/PyPOTS","repo_kind":"official","path":"pypots/nn/modules/stemgnn/backbone.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/stemgnn/backbone.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"95172885d816bacd"}},{"code_sha256_prefix":"d3cd3647cf2419ff","entry":"BackboneStemGNN","repo":"WenjieDu/PyPOTS","repo_kind":"official","path":"pypots/nn/modules/stemgnn/backbone.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/stemgnn/backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d3cd3647cf2419ff"}},{"code_sha256_prefix":"4f8c8fe870f963f4","entry":"Model","repo":"microsoft/StemGNN","repo_kind":"named_in_paper","path":"models/base_model.py","file_url":"https://github.com/microsoft/StemGNN/blob/HEAD/models/base_model.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":"4f8c8fe870f963f4"}},{"code_sha256_prefix":"6938e1bf74916676","entry":"StockBlockLayer","repo":"abdulmajid-murad/deep_probabilistic_forecast","repo_kind":"listed","path":"probabilistic_forecast/utils/gnn_utils.py","file_url":"https://github.com/abdulmajid-murad/deep_probabilistic_forecast/blob/HEAD/probabilistic_forecast/utils/gnn_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":"6938e1bf74916676"}},{"code_sha256_prefix":"2804726fa81f083b","entry":"StockBlockLayer","repo":"microsoft/StemGNN","repo_kind":"named_in_paper","path":"models/base_model.py","file_url":"https://github.com/microsoft/StemGNN/blob/HEAD/models/base_model.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":"2804726fa81f083b"}},{"code_sha256_prefix":"9f24f800c348e09a","entry":"StockBlockLayer","repo":"WenjieDu/PyPOTS","repo_kind":"official","path":"pypots/nn/modules/stemgnn/backbone.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/stemgnn/backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9f24f800c348e09a"}},{"code_sha256_prefix":"a5c63df6e233caf8","entry":"gconv","repo":"VeritasYin/STGCN_IJCAI-18","repo_kind":"found_in_text","path":"models/layers.py","file_url":"https://github.com/VeritasYin/STGCN_IJCAI-18/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a5c63df6e233caf8"}},{"code_sha256_prefix":"90cae9bd0b8c88e0","entry":"layer_norm","repo":"VeritasYin/STGCN_IJCAI-18","repo_kind":"found_in_text","path":"models/layers.py","file_url":"https://github.com/VeritasYin/STGCN_IJCAI-18/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"90cae9bd0b8c88e0"}},{"code_sha256_prefix":"5d06af05be3ee20b","entry":"spatio_conv_layer","repo":"VeritasYin/STGCN_IJCAI-18","repo_kind":"found_in_text","path":"models/layers.py","file_url":"https://github.com/VeritasYin/STGCN_IJCAI-18/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5d06af05be3ee20b"}},{"code_sha256_prefix":"dc4186fc31d8ef5c","entry":"st_conv_block","repo":"VeritasYin/STGCN_IJCAI-18","repo_kind":"found_in_text","path":"models/layers.py","file_url":"https://github.com/VeritasYin/STGCN_IJCAI-18/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dc4186fc31d8ef5c"}},{"code_sha256_prefix":"6126d5535e3ee910","entry":"temporal_conv_layer","repo":"VeritasYin/STGCN_IJCAI-18","repo_kind":"found_in_text","path":"models/layers.py","file_url":"https://github.com/VeritasYin/STGCN_IJCAI-18/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6126d5535e3ee910"}},{"code_sha256_prefix":"c9609eac116b4047","entry":"variable_summaries","repo":"VeritasYin/STGCN_IJCAI-18","repo_kind":"found_in_text","path":"models/layers.py","file_url":"https://github.com/VeritasYin/STGCN_IJCAI-18/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c9609eac116b4047"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}