{"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/mambats-improved-selective-state-space-models","title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","arxiv_id":"2405.16440","date":"2024-05-26","proceeding":null,"authors":["Xiuding Cai","Yaoyao Zhu","Xueyao Wang","Yu Yao"],"abstract":"In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state space models (SSMs), has emerged as a competitive alternative to Transformer, offering comparable performance with higher throughput and linear complexity related to sequence length. In this study, we analyze the limitations of current Mamba in LTSF and propose four targeted improvements, leading to MambaTS. We first introduce variable scan along time to arrange the historical information of all the variables together. We suggest that causal convolution in Mamba is not necessary for LTSF and propose the Temporal Mamba Block (TMB). We further incorporate a dropout mechanism for selective parameters of TMB to mitigate model overfitting. Moreover, we tackle the issue of variable scan order sensitivity by introducing variable permutation training. We further propose variable-aware scan along time to dynamically discover variable relationships during training and decode the optimal variable scan order by solving the shortest path visiting all nodes problem during inference. Extensive experiments conducted on eight public datasets demonstrate that MambaTS achieves new state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2405.16440v1","url_pdf":"https://arxiv.org/pdf/2405.16440v1.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":"mambats-improved-selective-state-space-models","repo_url":"https://github.com/XiudingCai/MambaTS-pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"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":"causal-convolution","method_name":"Causal Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"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":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.16440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16440"}},"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/XiudingCai/MambaTS-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_honours":1,"ran_draft_wrong":1,"ran_fixture":2,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"2af0df7394e58e06","entry":"conv1d_fft","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/ETSformer_EncDec.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/ETSformer_EncDec.py","link_basis":"harvester_set","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":"2af0df7394e58e06"}},{"code_sha256_prefix":"592ea8b254b006db","entry":"get_frequency_modes","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/FourierCorrelation.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/FourierCorrelation.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"592ea8b254b006db"}},{"code_sha256_prefix":"f32036738135c8a8","entry":"get_phi_psi","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/MultiWaveletCorrelation.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/MultiWaveletCorrelation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f32036738135c8a8"}},{"code_sha256_prefix":"4ef26472da51e3aa","entry":"legendreDer","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/MultiWaveletCorrelation.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/MultiWaveletCorrelation.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ef26472da51e3aa"}},{"code_sha256_prefix":"a54c8c5c47c6a8b8","entry":"phi_","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/MultiWaveletCorrelation.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/MultiWaveletCorrelation.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a54c8c5c47c6a8b8"}},{"code_sha256_prefix":"fd61ceb881a058a2","entry":"get_mask","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/Pyraformer_EncDec.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/Pyraformer_EncDec.py","link_basis":"harvester_set","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":"fd61ceb881a058a2"}},{"code_sha256_prefix":"05bdfb126191dbb0","entry":"refer_points","repo":"XiudingCai/MambaTS-pytorch","repo_kind":"official","path":"layers/Pyraformer_EncDec.py","file_url":"https://github.com/XiudingCai/MambaTS-pytorch/blob/HEAD/layers/Pyraformer_EncDec.py","link_basis":"harvester_set","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":"05bdfb126191dbb0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}