Aoran Wang

E03-0325-090

Maison du Nombre

6, avenue de la Fonte

L-4364 Esch-sur-Alzette

I am a PhD Student in computer science in the Faculty of Science, Technology and Medicine at the University of Luxembourg in Grand Duchy of Luxembourg.

My research is at the structural inference of dynamical systems with deep learning, which is at the interface of ODEs, Generative Models and Variational Methods. I am interested in helping researchers and machines to understand the interactions between the entities.

If you are interested in collaboration opportunities, please contact me at

aoran.wang@uni.lu

news

Jun 12, 2024	Our benchmark on LLMs’ ability to reason with educational knowledge graphs is now live!
Jun 10, 2024	Our benchmark on structural inference with synthetic data is now updated with more methods!
Feb 1, 2024	Joined Squirrel AI as a research intern.

selected publications

ICLR

Structural Inference with Dynamics Encoding and Partial Correlation Coefficients

Aoran Wang, and Jun Pang

In The Twelfth International Conference on Learning Representations 2024

Abs PDF Website

This paper introduces a novel approach to structural inference, combining a variational dynamics encoder with partial correlation coefficients. In contrast to prior methods, our approach leverages variational inference to encode node dynamics within latent variables, and structural reconstruction relies on the calculation of partial correlation coefficients derived from these latent variables. This unique design endows our method with scalability and extends its applicability to both one-dimensional and multi-dimensional feature spaces. Furthermore, by reorganizing latent variables according to temporal steps, our approach can effectively reconstruct directed graph structures. We validate our method through extensive experimentation on twenty datasets from a benchmark dataset and biological networks. Our results showcase the superior scalability, accuracy, and versatility of our proposed approach compared to existing methods. Moreover, experiments conducted on noisy data affirm the robustness of our method.
ICML

Effective and Efficient Structural Inference with Reservoir Computing

Aoran Wang, Tsz Pan Tong, and Jun Pang

In Proceedings of the 40th International Conference on Machine Learning 2023

Abs PDF Website

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.
ICML

Active Learning based Structural Inference

Aoran Wang, and Jun Pang

In Proceedings of the 40th International Conference on Machine Learning 2023

Abs PDF Website

In this paper, we propose a novel framework, Active Learning based Structural Inference (ALaSI), to infer the existence of directed connections from observed agents’ states over a time period in a dynamical system. With the help of deep active learning, ALaSI is competent in learning the representation of connections with a relatively small pool of prior knowledge. Moreover, based on information theory, the proposed inter- and out-of-scope message learning pipelines are remarkably beneficial to structural inference for large dynamical systems. We evaluate ALaSI on various large datasets including simulated systems and real-world networks, to demonstrate that ALaSI is able to outperform previous methods in precisely inferring the existence of connections in large systems under either supervised learning or unsupervised learning.
NeurIPS

Iterative Structural Inference of Directed Graphs

Aoran Wang, and Jun Pang

In Advances in Neural Information Processing Systems 2022

Abs PDF Website

In this paper, we propose a variational model, iterative Structural Inference of Directed Graphs (iSIDG), to infer the existence of directed interactions from observational agents’ features over a time period in a dynamical system. First, the iterative process in our model feeds the learned interactions back to encourage our model to eliminate indirect interactions and to emphasize directional representation during learning. Second, we show that extra regularization terms in the objective function for smoothness, connectiveness, and sparsity prompt our model to infer a more realistic structure and to further eliminate indirect interactions. We evaluate iSIDG on various datasets including biological networks, simulated fMRI data, and physical simulations to demonstrate that our model is able to precisely infer the existence of interactions, and is significantly superior to baseline models.