{"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/a-gated-mlp-architecture-for-learning","title":"Enhancing Topological Dependencies in Spatio-Temporal Graphs with Cycle Message Passing Blocks","arxiv_id":"2401.15894","date":"2024-01-29","proceeding":null,"authors":["Minho Lee","Yun Young Choi","Sun Woo Park","Seunghwan Lee","Joohwan Ko","Jaeyoung Hong"],"abstract":"Graph Neural Networks (GNNs) and Transformer-based models have been increasingly adopted to learn the complex vector representations of spatio-temporal graphs, capturing intricate spatio-temporal dependencies crucial for applications such as traffic datasets. Although many existing methods utilize multi-head attention mechanisms and message-passing neural networks (MPNNs) to capture both spatial and temporal relations, these approaches encode temporal and spatial relations independently, and reflect the graph's topological characteristics in a limited manner. In this work, we introduce the Cycle to Mixer (Cy2Mixer), a novel spatio-temporal GNN based on topological non-trivial invariants of spatio-temporal graphs with gated multi-layer perceptrons (gMLP). The Cy2Mixer is composed of three blocks based on MLPs: A temporal block for capturing temporal properties, a message-passing block for encapsulating spatial information, and a cycle message-passing block for enriching topological information through cyclic subgraphs. We bolster the effectiveness of Cy2Mixer with mathematical evidence emphasizing that our cycle message-passing block is capable of offering differentiated information to the deep learning model compared to the message-passing block. Furthermore, empirical evaluations substantiate the efficacy of the Cy2Mixer, demonstrating state-of-the-art performances across various spatio-temporal benchmark datasets. The source code is available at \\url{https://github.com/leemingo/cy2mixer}.","url_abs":"https://arxiv.org/abs/2401.15894v2","url_pdf":"https://arxiv.org/pdf/2401.15894v2.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":"a-gated-mlp-architecture-for-learning","repo_url":"https://github.com/leemingo/cy2mixer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"spatio-temporal-forecasting","task_name":"Spatio-Temporal Forecasting"},{"task_slug":"time-series-prediction","task_name":"Time Series Prediction"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-pems04","task":"Traffic Prediction","dataset":"PeMS04","model":"Cy2Mixer","rank_in_archive_order":4,"of":12,"metrics":{"12 Steps MAE":"18.14"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems07","task":"Traffic Prediction","dataset":"PeMS07","model":"Cy2Mixer","rank_in_archive_order":6,"of":17,"metrics":{"MAE@1h":"19.45"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems08","task":"Traffic Prediction","dataset":"PeMS08","model":"Cy2Mixer","rank_in_archive_order":6,"of":13,"metrics":{"MAE@1h":"13.53"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.15894","atlas_url":"https://app.syntology.ai/?focus=2401.15894","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}