{"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/autoregressive-moving-average-attention","title":"Autoregressive Moving-average Attention Mechanism for Time Series Forecasting","arxiv_id":"2410.03159","date":"2024-10-04","proceeding":null,"authors":["Jiecheng Lu","Xu Han","Yan Sun","Shihao Yang"],"abstract":"We propose an Autoregressive (AR) Moving-average (MA) attention structure that can adapt to various linear attention mechanisms, enhancing their ability to capture long-range and local temporal patterns in time series. In this paper, we first demonstrate that, for the time series forecasting (TSF) task, the previously overlooked decoder-only autoregressive Transformer model can achieve results comparable to the best baselines when appropriate tokenization and training methods are applied. Moreover, inspired by the ARMA model from statistics and recent advances in linear attention, we introduce the full ARMA structure into existing autoregressive attention mechanisms. By using an indirect MA weight generation method, we incorporate the MA term while maintaining the time complexity and parameter size of the underlying efficient attention models. We further explore how indirect parameter generation can produce implicit MA weights that align with the modeling requirements for local temporal impacts. Experimental results show that incorporating the ARMA structure consistently improves the performance of various AR attentions on TSF tasks, achieving state-of-the-art results.","url_abs":"https://arxiv.org/abs/2410.03159v1","url_pdf":"https://arxiv.org/pdf/2410.03159v1.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":"autoregressive-moving-average-attention","repo_url":"https://github.com/ljc-fvnr/arma-attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"arma","method_name":"ARMA"},{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.03159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03159"}},"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/ljc-fvnr/arma-attention","reach":null}],"summary":{"ran":1,"ran_draft_wrong":5},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"cf6a76a188797bee","entry":"CausalSelfAttentionARMA","repo":"ljc-fvnr/arma-attention","repo_kind":"official","path":"models/Autoregressive.py","file_url":"https://github.com/ljc-fvnr/arma-attention/blob/HEAD/models/Autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf6a76a188797bee"}},{"code_sha256_prefix":"453491f720bf2442","entry":"generate_attn_weight_from_qk","repo":"ljc-fvnr/arma-attention","repo_kind":"official","path":"models/Autoregressive.py","file_url":"https://github.com/ljc-fvnr/arma-attention/blob/HEAD/models/Autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"453491f720bf2442"}},{"code_sha256_prefix":"a3537d870e276aed","entry":"ma_k_activation","repo":"ljc-fvnr/arma-attention","repo_kind":"official","path":"models/Autoregressive.py","file_url":"https://github.com/ljc-fvnr/arma-attention/blob/HEAD/models/Autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3537d870e276aed"}},{"code_sha256_prefix":"fc041e8d3da65400","entry":"ma_q_activation","repo":"ljc-fvnr/arma-attention","repo_kind":"official","path":"models/Autoregressive.py","file_url":"https://github.com/ljc-fvnr/arma-attention/blob/HEAD/models/Autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc041e8d3da65400"}},{"code_sha256_prefix":"4c2d449452680949","entry":"ma_scaled_dot_product_attention","repo":"ljc-fvnr/arma-attention","repo_kind":"official","path":"models/Autoregressive.py","file_url":"https://github.com/ljc-fvnr/arma-attention/blob/HEAD/models/Autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c2d449452680949"}},{"code_sha256_prefix":"a6ef6de38bc2425f","entry":"ma_scaled_dot_product_attention","repo":"ljc-fvnr/arma-attention","repo_kind":"official","path":"models/Autoregressive.py","file_url":"https://github.com/ljc-fvnr/arma-attention/blob/HEAD/models/Autoregressive.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6ef6de38bc2425f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}