{"ID":2865901,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20968","arxiv_id":"2509.20968","title":"Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning","abstract":"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.","short_abstract":"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 ef...","url_abs":"https://arxiv.org/abs/2509.20968","url_pdf":"https://arxiv.org/pdf/2509.20968v1","authors":"[\"Zhengyuan Shi\",\"Jingxin Wang\",\"Wentao Jiang\",\"Chengyu Ma\",\"Ziyang Zheng\",\"Zhufei Chu\",\"Weikang Qian\",\"Qiang Xu\"]","published":"2025-09-25T10:12:04Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}