XOR-CD: Linearly Convergent Constrained Structure Generation

Fan Ding, Jianzhu Ma, Jinbo Xu, Yexiang Xue
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2728-2738, 2021.

Abstract

We propose XOR-Contrastive Divergence learning (XOR-CD), a provable approach for constrained structure generation, which remains difficult for state-of-the-art neural network and constraint reasoning approaches. XOR-CD harnesses XOR-Sampling to generate samples from the model distribution in CD learning and is guaranteed to generate valid structures. In addition, XOR-CD has a linear convergence rate towards the global maximum of the likelihood function within a vanishing constant in learning exponential family models. Constraint satisfaction enabled by XOR-CD also boosts its learning performance. Our real-world experiments on data-driven experimental design, dispatching route generation, and sequence-based protein homology detection demonstrate the superior performance of XOR-CD compared to baseline approaches in generating valid structures as well as capturing the inductive bias in the training set.

Cite this Paper


BibTeX
@InProceedings{pmlr-v139-ding21a, title = {XOR-CD: Linearly Convergent Constrained Structure Generation}, author = {Ding, Fan and Ma, Jianzhu and Xu, Jinbo and Xue, Yexiang}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {2728--2738}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/ding21a/ding21a.pdf}, url = {https://proceedings.mlr.press/v139/ding21a.html}, abstract = {We propose XOR-Contrastive Divergence learning (XOR-CD), a provable approach for constrained structure generation, which remains difficult for state-of-the-art neural network and constraint reasoning approaches. XOR-CD harnesses XOR-Sampling to generate samples from the model distribution in CD learning and is guaranteed to generate valid structures. In addition, XOR-CD has a linear convergence rate towards the global maximum of the likelihood function within a vanishing constant in learning exponential family models. Constraint satisfaction enabled by XOR-CD also boosts its learning performance. Our real-world experiments on data-driven experimental design, dispatching route generation, and sequence-based protein homology detection demonstrate the superior performance of XOR-CD compared to baseline approaches in generating valid structures as well as capturing the inductive bias in the training set.} }
Endnote
%0 Conference Paper %T XOR-CD: Linearly Convergent Constrained Structure Generation %A Fan Ding %A Jianzhu Ma %A Jinbo Xu %A Yexiang Xue %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-ding21a %I PMLR %P 2728--2738 %U https://proceedings.mlr.press/v139/ding21a.html %V 139 %X We propose XOR-Contrastive Divergence learning (XOR-CD), a provable approach for constrained structure generation, which remains difficult for state-of-the-art neural network and constraint reasoning approaches. XOR-CD harnesses XOR-Sampling to generate samples from the model distribution in CD learning and is guaranteed to generate valid structures. In addition, XOR-CD has a linear convergence rate towards the global maximum of the likelihood function within a vanishing constant in learning exponential family models. Constraint satisfaction enabled by XOR-CD also boosts its learning performance. Our real-world experiments on data-driven experimental design, dispatching route generation, and sequence-based protein homology detection demonstrate the superior performance of XOR-CD compared to baseline approaches in generating valid structures as well as capturing the inductive bias in the training set.
APA
Ding, F., Ma, J., Xu, J. & Xue, Y.. (2021). XOR-CD: Linearly Convergent Constrained Structure Generation. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:2728-2738 Available from https://proceedings.mlr.press/v139/ding21a.html.

Related Material