Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918147946184704 |
|---|---|
| author | Shi, Zhengyuan Wang, Jingxin Jiang, Wentao Ma, Chengyu Zheng, Ziyang Chu, Zhufei Qian, Weikang Xu, Qiang |
| author_facet | Shi, Zhengyuan Wang, Jingxin Jiang, Wentao Ma, Chengyu Zheng, Ziyang Chu, Zhufei Qian, Weikang Xu, Qiang |
| contents | Multiview learning on Boolean circuits holds immense promise, as different graph-based representations offer complementary structural and semantic information. However, the vast structural heterogeneity between views, such as an And-Inverter Graph (AIG) versus an XOR-Majority Graph (XMG), poses a critical barrier to effective fusion, especially for self-supervised techniques like masked modeling. Naively applying such methods fails, as the cross-view context is perceived as noise. Our key insight is that functional alignment is a necessary precondition to unlock the power of multiview self-supervision. We introduce MixGate, a framework built on a principled training curriculum that first teaches the model a shared, function-aware representation space via an Equivalence Alignment Loss. Only then do we introduce a multiview masked modeling objective, which can now leverage the aligned views as a rich, complementary signal. Extensive experiments, including a crucial ablation study, demonstrate that our alignment-first strategy transforms masked modeling from an ineffective technique into a powerful performance driver. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20968 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning Shi, Zhengyuan Wang, Jingxin Jiang, Wentao Ma, Chengyu Zheng, Ziyang Chu, Zhufei Qian, Weikang Xu, Qiang Machine Learning Multiview learning on Boolean circuits holds immense promise, as different graph-based representations offer complementary structural and semantic information. However, the vast structural heterogeneity between views, such as an And-Inverter Graph (AIG) versus an XOR-Majority Graph (XMG), poses a critical barrier to effective fusion, especially for self-supervised techniques like masked modeling. Naively applying such methods fails, as the cross-view context is perceived as noise. Our key insight is that functional alignment is a necessary precondition to unlock the power of multiview self-supervision. We introduce MixGate, a framework built on a principled training curriculum that first teaches the model a shared, function-aware representation space via an Equivalence Alignment Loss. Only then do we introduce a multiview masked modeling objective, which can now leverage the aligned views as a rich, complementary signal. Extensive experiments, including a crucial ablation study, demonstrate that our alignment-first strategy transforms masked modeling from an ineffective technique into a powerful performance driver. |
| title | Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.20968 |