Revisiting Convolution Architecture in the Realm of DNA Foundation Models
Keywords: DNA modeling, foundation model, Genomic Language Model, Representation Learning
Abstract: In recent years, A variety of methods based on Transformer and state space model (SSM) architectures have been proposed, advancing foundational DNA language models.
However, there is a lack of comparison between these recent approaches and the classical architecture—convolutional networks (CNNs)—on foundation model benchmarks.
This raises the question: are CNNs truly being surpassed by these recent approaches based on transformer and SSM architectures? In this paper, we develop a simple yet well-designed CNN-based method, named ConvNova. ConvNova identifies and proposes three effective designs: 1) dilated convolutions, 2) gated convolutions, and 3) a dual-branch framework for gating mechanisms.
Through extensive empirical experiments, we demonstrate that ConvNova significantly outperforms recent methods on more than half of the tasks across several foundation model benchmarks. For example, in histone-related tasks, ConvNova surpasses the second-best method by an average of 5.8\%, while generally utilizing fewer parameters and enabling faster computation. Additionally, the experiments observed findings that may be related to biological characteristics. This indicates that CNNs are still a strong competitor compared to Transformers and SSMs. We anticipate that this work will spark renewed interest in CNN-based methods for DNA foundation models.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1899
Loading