Effective and Efficient Structural Inference with Reservoir Computing

Aoran Wang, Tsz Pan Tong, Jun Pang
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36391-36410, 2023.

Abstract

In this paper, we present an effective and efficient structural inference approach by integrating a Reservoir Computing (RC) network into a Variational Auto-encoder-based (VAE-based) structural inference framework. With the help of Bi-level Optimization, the backbone VAE-based method follows the Information Bottleneck principle and infers a general adjacency matrix in its latent space; the RC net substitutes the partial role of the decoder and encourages the whole approach to perform further steps of gradient descent based on limited available data. The experimental results on various datasets including biological networks, simulated fMRI data, and physical simulations show the effectiveness and efficiency of our proposed method for structural inference, either with much fewer trajectories or with much shorter trajectories compared with previous works.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-wang23ak, title = {Effective and Efficient Structural Inference with Reservoir Computing}, author = {Wang, Aoran and Tong, Tsz Pan and Pang, Jun}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {36391--36410}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/wang23ak/wang23ak.pdf}, url = {https://proceedings.mlr.press/v202/wang23ak.html}, abstract = {In this paper, we present an effective and efficient structural inference approach by integrating a Reservoir Computing (RC) network into a Variational Auto-encoder-based (VAE-based) structural inference framework. With the help of Bi-level Optimization, the backbone VAE-based method follows the Information Bottleneck principle and infers a general adjacency matrix in its latent space; the RC net substitutes the partial role of the decoder and encourages the whole approach to perform further steps of gradient descent based on limited available data. The experimental results on various datasets including biological networks, simulated fMRI data, and physical simulations show the effectiveness and efficiency of our proposed method for structural inference, either with much fewer trajectories or with much shorter trajectories compared with previous works.} }
Endnote
%0 Conference Paper %T Effective and Efficient Structural Inference with Reservoir Computing %A Aoran Wang %A Tsz Pan Tong %A Jun Pang %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-wang23ak %I PMLR %P 36391--36410 %U https://proceedings.mlr.press/v202/wang23ak.html %V 202 %X In this paper, we present an effective and efficient structural inference approach by integrating a Reservoir Computing (RC) network into a Variational Auto-encoder-based (VAE-based) structural inference framework. With the help of Bi-level Optimization, the backbone VAE-based method follows the Information Bottleneck principle and infers a general adjacency matrix in its latent space; the RC net substitutes the partial role of the decoder and encourages the whole approach to perform further steps of gradient descent based on limited available data. The experimental results on various datasets including biological networks, simulated fMRI data, and physical simulations show the effectiveness and efficiency of our proposed method for structural inference, either with much fewer trajectories or with much shorter trajectories compared with previous works.
APA
Wang, A., Tong, T.P. & Pang, J.. (2023). Effective and Efficient Structural Inference with Reservoir Computing. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:36391-36410 Available from https://proceedings.mlr.press/v202/wang23ak.html.

Related Material