Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms

Aoran Wang, Xinnan Dai, Jun Pang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62761-62783, 2025.

Abstract

Existing methods for inferring latent relational structures struggle to integrate partial prior knowledge, such as known edges, node-degree constraints, and global sparsity, without destabilizing training or conflicting with probabilistic assumptions. We propose Soft-Gated Structural Inference (SGSI), a VAE framework that seamlessly incorporates domain constraints via (1) soft gating with learnable edge masks to preserve gradients, (2) cloning-clamping of deterministic edges to avoid distributional conflicts, and (3) adaptive regularization to balance data-driven learning with domain constraints. By excluding known edges from stochastic inference, SGSI reallocates capacity to uncertain interactions, optimizing the information bottleneck trade-off. Experiments on 16 datasets show SGSI improves edge recovery by up to $9$% AUROC over baselines, scales to larger graphs ($94.2$% AUROC), and maintains stable training. SGSI bridges domain expertise with data-driven learning, enabling interpretable and robust structural discovery in dynamical systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25w, title = {Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms}, author = {Wang, Aoran and Dai, Xinnan and Pang, Jun}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {62761--62783}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25w/wang25w.pdf}, url = {https://proceedings.mlr.press/v267/wang25w.html}, abstract = {Existing methods for inferring latent relational structures struggle to integrate partial prior knowledge, such as known edges, node-degree constraints, and global sparsity, without destabilizing training or conflicting with probabilistic assumptions. We propose Soft-Gated Structural Inference (SGSI), a VAE framework that seamlessly incorporates domain constraints via (1) soft gating with learnable edge masks to preserve gradients, (2) cloning-clamping of deterministic edges to avoid distributional conflicts, and (3) adaptive regularization to balance data-driven learning with domain constraints. By excluding known edges from stochastic inference, SGSI reallocates capacity to uncertain interactions, optimizing the information bottleneck trade-off. Experiments on 16 datasets show SGSI improves edge recovery by up to $9$% AUROC over baselines, scales to larger graphs ($94.2$% AUROC), and maintains stable training. SGSI bridges domain expertise with data-driven learning, enabling interpretable and robust structural discovery in dynamical systems.} }
Endnote
%0 Conference Paper %T Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms %A Aoran Wang %A Xinnan Dai %A Jun Pang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25w %I PMLR %P 62761--62783 %U https://proceedings.mlr.press/v267/wang25w.html %V 267 %X Existing methods for inferring latent relational structures struggle to integrate partial prior knowledge, such as known edges, node-degree constraints, and global sparsity, without destabilizing training or conflicting with probabilistic assumptions. We propose Soft-Gated Structural Inference (SGSI), a VAE framework that seamlessly incorporates domain constraints via (1) soft gating with learnable edge masks to preserve gradients, (2) cloning-clamping of deterministic edges to avoid distributional conflicts, and (3) adaptive regularization to balance data-driven learning with domain constraints. By excluding known edges from stochastic inference, SGSI reallocates capacity to uncertain interactions, optimizing the information bottleneck trade-off. Experiments on 16 datasets show SGSI improves edge recovery by up to $9$% AUROC over baselines, scales to larger graphs ($94.2$% AUROC), and maintains stable training. SGSI bridges domain expertise with data-driven learning, enabling interpretable and robust structural discovery in dynamical systems.
APA
Wang, A., Dai, X. & Pang, J.. (2025). Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:62761-62783 Available from https://proceedings.mlr.press/v267/wang25w.html.

Related Material