Jiameng Fan

Dr. Jiameng Fan

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 October 2020
Verified
Book Chapter
Closed access
PDF file
JFJiameng Fan
Jiameng Fan
CHChao Huang
Chao Huang
XCXin Chen
Xin Chen
WLWenchao Li
Wenchao Li
QZQi Zhu
Qi Zhu


8 November 2023 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
YWYixuan Wang
Yixuan Wang
WZWeichao Zhou
Weichao Zhou
JFJiameng Fan
Jiameng Fan
ZWZhilu Wang
Zhilu Wang
JLJiajun Li
Jiajun Li
QZQi Zhu
Qi Zhu
Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performance on challenging control problems. However, the potential adoption of NN controllers in real-life applications has been significantly impeded by the growing concerns over the safety of these NN-controlled systems (NNCSs). In this work, we present POLAR-Express, an efficient and precise formal reachability analysis tool for verifying the safety of NNCSs. POLAR-Express uses Taylor model (TM) arithmetic to propagate TMs layer-by-layer across an NN to compute an overapproximation of the NN. It can be applied to analyze any feedforward NNs with continuous activation functions, such as ReLU, Sigmoid, and Tanh activation functions that cover the common benchmarks for NNCS reachability analysis. Compared with its earlier prototype POLAR, we develop a novel approach in POLAR-Express to propagate TMs more efficiently and precisely across ReLU activation functions, and provide parallel computation support for TM propagation, thus significantly improving the efficiency and scalability. Across the comparison with six other state-of-the-art tools on a diverse set of common benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis. POLAR-Express is publicly available at https://github.com/ChaoHuang2018/POLAR_Tool .

2 October 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
CHChao Huang
Chao Huang
JFJiameng Fan
Jiameng Fan
XCXin Chen
Xin Chen
WLWenchao Li
Wenchao Li
QZQi Zhu
Qi Zhu
In this article, we present a layer-wise refinement method for neural network output range analysis. While approaches such as nonlinear programming (NLP) can directly model the high nonlinearity brought by neural networks in output range analysis, they are known to be difficult to solve in general. We propose to use a convex polygonal relaxation (overapproximation) of the activation functions to cope with the nonlinearity. This allows us to encode the relaxed problem into a mixed-integer linear program (MILP), and control the tightness of the relaxation by adjusting the number of segments in the polygon. Starting with a segment number of 1 for each neuron, which coincides with a linear programming (LP) relaxation, our approach selects neurons layer by layer to iteratively refine this relaxation. To tackle the increase of the number of integer variables with tighter refinement, we bridge the propagation-based method and the programming-based method by dividing and sliding the layer-wise constraints. Specifically, given a sliding number $s$ , for the neurons in layer $l$ , we only encode the constraints of the layers between $l-s$ and $l$ . We show that our overall framework is sound and provides a valid overapproximation. Experiments on deep neural networks demonstrate significant improvement on output range analysis precision using our approach compared to the state-of-the-art.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
FFFeisi Fu
Feisi Fu
ZWZhilu Wang
Zhilu Wang
WZWeichao Zhou
Weichao Zhou
YWYixuan Wang
Yixuan Wang
JFJiameng Fan
Jiameng Fan
WLWenchao Li
Wenchao Li
We present REGLO, a novel methodology for repairing pretrained neural networks to satisfy global robustness and individual fairness properties. A neural network is said to be globally robust with respect to a given input region if and only if all the input points in the region are locally robust. This notion of global robustness also captures the notion of individual fairness as a special case. We prove that any counterexample to a global robustness property must exhibit a corresponding large gradient. For ReLU networks, this result allows us to efficiently identify the linear regions that violate a given global robustness property. By formulating and solving a suitable robust convex optimization problem, REGLO then computes a minimal weight change that will provably repair these violating linear regions.

24 December 2022 in arXiv
Verified
Preprint
Open access
PDF file
CHChao Huang
Chao Huang
JFJiameng Fan
Jiameng Fan
ZWZhilu Wang
Zhilu Wang
YWYixuan Wang
Yixuan Wang
WZWeichao Zhou
Weichao Zhou
QZQi Zhu
Qi Zhu
We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs). Existing approaches that leverage the standard Taylor Model (TM) arithmetic for approximating the neural-network controller cannot deal with non-differentiable activation functions and suffer from rapid explosion of the remainder when propagating the TMs. POLAR overcomes these shortcomings by integrating TM arithmetic with \textbf{Bernstein B{\'e}zier Form} and \textbf{symbolic remainder}. The former enables TM propagation across non-differentiable activation functions and local refinement of TMs, and the latter reduces error accumulation in the TM remainder for linear mappings in the network. Experimental results show that POLAR significantly outperforms the current state-of-the-art tools in terms of both efficiency and tightness of the reachable set overapproximation. The source code can be found in https://github.com/ChaoHuang2018/POLAR_Tool