arXiv subjects

Zixi Wang

Publications and source records attributed to Zixi Wang.

23 records · Page 2Linked to original sources

arXiv2024

Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learning

Graphs are typical non-Euclidean data of complex structures. In recent years, Riemannian graph representation learning has emerged as an exciting alternative to Euclidean ones. However, Riemannian methods are still in an early stage: most of them present a single curvature (radius) regardless of structural complexity, suffer from numerical instability due to the exponential/logarithmic map, and lack the ability to capture motif regularity. In light of the issues above, we propose the problem of \emph{Motif-aware Riemannian Graph Representation Learning}, seeking a numerically stable encoder to capture motif regularity in a diverse-curvature manifold without labels. To this end, we present a novel Motif-aware Riemannian model with Generative-Contrastive learning (MotifRGC), which conducts a minmax game in Riemannian manifold in a self-supervised manner. First, we propose a new type of Riemannian GCN (D-GCN), in which we construct a diverse-curvature manifold by a product layer with the diversified factor, and replace the exponential/logarithmic map by a stable kernel layer. Second, we introduce a motif-aware Riemannian generative-contrastive learning to capture motif regularity in the constructed manifold and learn motif-aware node representation without external labels. Empirical results show the superiority of MofitRGC.

cs.LG↗

arXiv2023

Monitoring and Adapting ML Models on Mobile Devices

ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to track their accuracy, which can degrade unpredictably (e.g., due to data drift). We design the first end-to-end system for continuously monitoring and adapting models on mobile devices without requiring feedback from users. Our key observation is that often model degradation is due to a specific root cause, which may affect a large group of devices. Therefore, once the system detects a consistent degradation across a large number of devices, it employs a root cause analysis to determine the origin of the problem and applies a cause-specific adaptation. We evaluate the system on two computer vision datasets, and show it consistently boosts accuracy compared to existing approaches. On a dataset containing photos collected from driving cars, our system improves the accuracy on average by 15%.

cs.LG↗

arXiv2023

On profinite rigidity of 4-dimensional Seifert manifolds

There are many results showing the connection and phenomenon between some low-dimensional manifolds with the profinite completions of their fundamental groups. We focus on some Seifert 4-manifolds about the extent of their profinite completion to detect one, giving classification of monodromies and conditions for them to be profinitely rigid.

math.GT↗

arXiv2022

High Noise Immune Time-domain Inversion via Cascade Network (TICaN) for Complex Scatterers

In this paper, a high noise immune time-domain inversion cascade network (TICaN) is proposed to reconstruct scatterers from the measured electromagnetic fields. The TICaN is comprised of a denoising block aiming at improving the signal-to-noise ratio, and an inversion block to reconstruct the electromagnetic properties from the raw time-domain measurements. The scatterers investigated in this study include complicated geometry shapes and high contrast, which cover the stratum layer, lossy medium and hyperfine structure, etc. After being well trained, the performance of the TICaN is evaluated from the perspective of accuracy, noise-immunity, computational acceleration, and generalizability. It can be proven that the proposed framework can realize high-precision inversion under high-intensity noise environments. Compared with traditional reconstruction methods, TICaN avoids the tedious iterative calculation by utilizing the parallel computing ability of GPU and thus significantly reduce the computing time. Besides, the proposed TICaN has certain generalization ability in reconstructing the unknown scatterers such as the famous Austria rings. Herein, it is confident that the proposed TICaN will serve as a new path for real-time quantitative microwave imaging for various practical scenarios.

eess.SP↗

arXiv2021

Distinguishing 4-dimensional geometries via profinite completions

It is well-known that there are 19 classes of geometries for 4-dimensional manifolds in the sense of Thurston. We could ask that to what extent the geometric information is revealed by the profinite completion of the fundamental group of a closed smooth geometric 4-manifold. In this paper, we show that the geometry of a closed orientable 4-manifold in the sense of Thurston could be detected by the profinite completion of its fundamental group except when the geometry is $ \mathbb{H}^{4}$, $\mathbb{H}^{2}_{\mathbb{C}}$ or $\mathbb{H}^2 \times \mathbb{H}^2$. Moreover, despite the fact that not every smooth 4-manifold could admit one geometry in the sense of Thurston, some 4-dimensional manifolds with Seifert fibred structures are indeed geometric. For a closed orientable Seifert fibred 4-manifold $M$, we show that whether $M$ is geometric could be detected by the profinite completion of its fundamental group.

math.GT↗