arXiv subjects

Jihong Wang

Publications and source records attributed to Jihong Wang.

28 records · Page 2Linked to original sources

arXiv2022

Disentangled Generation with Information Bottleneck for Few-Shot Learning

Few-shot learning (FSL), which aims to classify unseen classes with few samples, is challenging due to data scarcity. Although various generative methods have been explored for FSL, the entangled generation process of these methods exacerbates the distribution shift in FSL, thus greatly limiting the quality of generated samples. To these challenges, we propose a novel Information Bottleneck (IB) based Disentangled Generation Framework for FSL, termed as DisGenIB, that can simultaneously guarantee the discrimination and diversity of generated samples. Specifically, we formulate a novel framework with information bottleneck that applies for both disentangled representation learning and sample generation. Different from existing IB-based methods that can hardly exploit priors, we demonstrate our DisGenIB can effectively utilize priors to further facilitate disentanglement. We further prove in theory that some previous generative and disentanglement methods are special cases of our DisGenIB, which demonstrates the generality of the proposed DisGenIB. Extensive experiments on challenging FSL benchmarks confirm the effectiveness and superiority of DisGenIB, together with the validity of our theoretical analyses. Our codes will be open-source upon acceptance.

cs.CV↗

arXiv2022

Stability and convergence analysis of high-order numerical schemes with DtN-type absorbing boundary conditions for nonlocal wave equations

The stability and convergence analysis of high-order numerical approximations for the one- and two-dimensional nonlocal wave equations on unbounded spatial domains are considered. We first use the quadrature-based finite difference schemes to discretize the spatially nonlocal operator, and apply the explicit difference scheme to approximate the temporal derivative to achieve a fully discrete infinity system. After that, we construct the Dirichlet-to-Neumann (DtN)-type absorbing boundary conditions (ABCs) to reduce the infinite discrete system into a finite discrete system. To do so, we first adopt the idea in [Du, Zhang and Zheng, \emph{Commun. Comput. Phys.}, 24(4):1049--1072, 2018 and Du, Han, Zhang and Zheng, \emph{SIAM J. Sci. Comp.}, 40(3):A1430--A1445, 2018] to derive the Dirichlet-to-Dirichlet (DtD)-type mappings for one- and two-dimensional cases, respectively. We then use the discrete nonlocal Green's first identity to achieve the discrete DtN-type mappings from the DtD-type mappings. The resulting DtN-type mappings make it possible to perform the stability and convergence analysis of the reduced problem. Numerical experiments are provided to demonstrate the accuracy and effectiveness of the proposed approach.

math.NA↗

arXiv2022

Towards Explanation for Unsupervised Graph-Level Representation Learning

Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}" Existing explanation methods focus on the supervised settings, \eg, node classification and graph classification, while the explanation for unsupervised graph-level representation learning is still unexplored. The opaqueness of the graph representations may lead to unexpected risks when deployed for high-stake decision-making scenarios. In this paper, we advance the Information Bottleneck principle (IB) to tackle the proposed explanation problem for unsupervised graph representations, which leads to a novel principle, \textit{Unsupervised Subgraph Information Bottleneck} (USIB). We also theoretically analyze the connection between graph representations and explanatory subgraphs on the label space, which reveals that the expressiveness and robustness of representations benefit the fidelity of explanatory subgraphs. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our developed explainer and the validity of our theoretical analysis.

cs.LG↗

arXiv2022

Remarkably strong magnetic response in molecules with polar groups

For more than a century, electricity and magnetism have been believed to always exhibit inextricable link due to the symmetry in electromagnetism. At the interface, polar groups that have polar charges, are indispensable to be considered, which interact directly with other polar charges/external charges/external electric fields. However, there is no report on the corresponding magnetic properties on these polar groups. Clearly, such asymmetry, that is, only the interaction between the polar groups and charges, is out of bounds. Here we show that those molecules with considerable polar groups, such as cellulose acetate (CA) and other cellulose derivatives with different polar groups, can have strong magnetic response, indicating that they are strongly paramagnetic. Density functional theory (DFT) calculation shows that the polarity greatly reduces the excitation energy from the state without net spin (singlet) to the state with net spin (triplet), making the considerable existence of magnetic moments on the polar groups. We note that the hydrophobic groups in these molecules have no magnetic moments, however, they make the molecules aggregate to amply the magnetic effect of the magnetic moments in the polar groups, so that these magnetic moments can induce the strong paramagnetism. Our observations suggest a recovery of the symmetry with inextricable link between the electricity and magnetism at the interface. The findings leave many imaginations of the role of the magnetic interaction in biological systems as well as other magnetic applications considering that many of those polar materials are biological materials, pharmaceutical materials, chemical raw materials, and even an essential hormone in agricultural production.

cond-mat.soft↗

arXiv2021

Super strong paramagnetism induced by polar functional groups and water

We experimentally demonstrate that some commonly used materials such as cellulose acetate and chitin which are traditionally considered to be non-magnetic show super strong paramagnetism in aqueous solutions under ambient conditions when they are agglomerated by nanoparticles. Theoretical computations show that strongly polar functional groups can reduce the potential barrier for a singlet-triplet interconversion with the help of surrounding water, inducing the magnetic moments. These magnetic moments distributed on the surfaces of the nanoparticles, which make a large number of magnetic moments gather in a very small space, greatly enhance the alignment of the moments along and amplify the effect of the external magnetic field, resulting in the super strong paramagnetism. Our findings suggest that the polar functional group may always induce paramagnetism and the magnetic effect may be universal as the electric effects since the polarization is very common in materials.

cond-mat.soft↗

arXiv2020

Super strong paramagnetism of aromatic peptides adsorbed with monovalent cations

We experimentally demonstrated that the AYFFF self-assemblies adsorbed with various monovalent cations (Na+, K+, and Li+) show unexpectedly super strong paramagnetism. The key to the super strong paramagnetism lies in the hydrated cation-π interactions between the monovalent cations and the aromatic rings in the AYFFF assemblies, which endows the AYFFF-cations complex with magnetic moments.

physics.bio-ph↗

arXiv2020

Unexpectedly super strong paramagnetism of aromatic peptides due to cations of divalent metals

The magnetism of most biological systems has not been characterized, which directly impedes our understanding of many magnetic field-related phenomena, including magnetoreception and magnetic bio-effects. Here we measured the magnetic susceptibility of aromatic peptide AYFFF self-assemblies in the presence or absence of divalent metal cations in liquid phase at room temperature. Unexpectedly, the magnetic susceptibilities of AYFFF self-assemblies in the chloride solution of various divalent cations (Mg2+, Zn2+, and Cu2+) show super strong paramagnetism. We attribute the super strong paramagnetism to existence of the magnetic moments on the cations adsorbed on aromatic rings in the AYFFF assemblies through hydrated cation-π interactions, where the adsorbed cations display non-divalent behavior with unpaired electron spins. Our results indicate the super strong paramagnetism or potential ferromagnetism in the aromatic ring-enriched biomolecules when there are enough cations of divalent metals adsorbed. The findings not only provide fundamental information for understanding the magnetism of biological systems, provoke insights for investigating the origin of magnetoreception and bio-effects of magnetic fields, but also help developing future magnetic-control techniques on aromatic ring-enriched biomolecules and drugs in living organisms, as well as biomaterial fabrication and manipulation.

cond-mat.soft↗

arXiv2020

Implicit bias with Ritz-Galerkin method in understanding deep learning for solving PDEs

This paper aims at studying the difference between Ritz-Galerkin (R-G) method and deep neural network (DNN) method in solving partial differential equations (PDEs) to better understand deep learning. To this end, we consider solving a particular Poisson problem, where the information of the right-hand side of the equation f is only available at n sample points, that is, f is known at finite sample points. Through both theoretical and numerical studies, we show that solution of the R-G method converges to a piecewise linear function for the one dimensional (1D) problem or functions of lower regularity for high dimensional problems. With the same setting, DNNs however learn a relative smooth solution regardless of the dimension, this is, DNNs implicitly bias towards functions with more low-frequency components among all functions that can fit the equation at available data points. This bias is explained by the recent study of frequency principle (Xu et al., (2019) [17] and Zhang et al., (2019) [11, 19]). In addition to the similarity between the traditional numerical methods and DNNs in the approximation perspective, our work shows that the implicit bias in the learning process, which is different from traditional numerical methods, could help better understand the characteristics of DNNs.

math.NA↗

arXiv2020

Scalable Attack on Graph Data by Injecting Vicious Nodes

Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations. However, a vast majority of existing works cannot handle large-scale graphs because of their high time complexity. Additionally, existing works mainly focus on manipulating existing nodes on the graph, while in practice, attackers usually do not have the privilege to modify information of existing nodes. In this paper, we develop a more scalable framework named Approximate Fast Gradient Sign Method (AFGSM) which considers a more practical attack scenario where adversaries can only inject new vicious nodes to the graph while having no control over the original graph. Methodologically, we provide an approximation strategy to linearize the model we attack and then derive an approximate closed-from solution with a lower time cost. To have a fair comparison with existing attack methods that manipulate the original graph, we adapt them to the new attack scenario by injecting vicious nodes. Empirical experimental results show that our proposed attack method can significantly reduce the classification accuracy of GCNs and is much faster than existing methods without jeopardizing the attack performance.

cs.CR↗

arXiv2020

A modular phantom and software to characterize 3D geometric distortion in MRI

MRI offers outstanding soft tissue contrast that may reduce uncertainties in target and organ-at-risk delineation and enable online adaptive image-guided treatment. Spatial distortions resulting from non-linearities in the gradient fields and non-uniformity in the main magnetic field must be accounted for across the imaging field-of-view to prevent systematic errors during treatment delivery. This work presents a modular phantom and software application to characterize geometric distortion (GD) within the large field-of-view MRI images required for radiation therapy simulation. The modular phantom is assembled from a series of rectangular foam blocks containing high-contrast fiducial markers in a known configuration. The modular phantom design facilitates transportation of the phantom between different MR scanners and MR-guided linear accelerators and allows the phantom to be adapted to fit different sized bores or coils. The phantom was evaluated using a 1.5T MR-guided linear accelerator (MR-Linac) and 1.5T and 3.0T diagnostic scanners. Performance was assessed by varying acquisition parameters to induce image distortions in a known manner. Imaging was performed using T1 and T2 weighted pulse sequences with 2D and 3D distortion correction algorithms and the receiver bandwidth (BW) varied as 250-815 Hz/pixel. Phantom set-up reproducibility was evaluated across independent set-ups. The software was validated by comparison with a non-modular phantom. Average geometric distortion was 0.94+/-0.58 mm for the MR-Linac, 0.90+/-0.53 mm for the 1.5 T scanner, and 1.15+/-0.62 mm for the 3.0T scanner, for a 400 mm diameter volume-of-interest. GD increased, as expected, with decreasing BW, and with the 2D versus 3D correction algorithm. Differences in GD attributed to phantom set-up were 0.13 mm or less. Differences in GD for the two software applications were less than 0.07 mm.

physics.med-ph↗