{"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/spectraformer-a-unified-random-feature","title":"Spectraformer: A Unified Random Feature Framework for Transformer","arxiv_id":"2405.15310","date":"2024-05-24","proceeding":null,"authors":["Duke Nguyen","Aditya Joshi","Flora Salim"],"abstract":"Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods use a subset of combinations of component functions and weight matrices within the random features paradigm. We identify the need for a systematic comparison of different combinations of weight matrices and component functions for attention learning in Transformer. In this work, we introduce Spectraformer, a unified framework for approximating and learning the kernel function in linearized attention of the Transformer. We experiment with broad classes of component functions and weight matrices for three textual tasks in the LRA benchmark. Our empirical findings indicate that different kernels are good at different tasks and that kernel choice is fundamental to performant models. Our code is available at: https://github.com/dukenguyenxyz/spectraformer .","url_abs":"https://arxiv.org/abs/2405.15310v3","url_pdf":"https://arxiv.org/pdf/2405.15310v3.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":"spectraformer-a-unified-random-feature","repo_url":"https://github.com/dukenguyenxyz/spectraformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"spectraformer-a-unified-random-feature","repo_url":"https://github.com/dukeraphaelng/spectraformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"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":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}