arXiv subjects

Zijian Zhou

Publications and source records attributed to Zijian Zhou.

At least 73 records · Page 4Linked to original sources

arXiv2025

Challenging the Law of Energy Conservation Through Superposed Waves Based on Spatial Symmetry of Two RF Sources: Theoretical Derivation and Experimental Verification

This study is grounded in the concept of spatial symmetry, which allows two co-phase RF sources to jointly radiate harmonic electromagnetic (EM) waves, even in presence of electromagnetic couplings between them. The superposition law is directly applied to the two waves owing to their sources, including the EM coupling effects. Our research uncovers a conflict with energy conservation law at the following two levels: (1) the total radiative powers as defined by Poynting theorem, and (2) further, the input powers of the sources. To explore this phenomenon, we create a symmetric dipole model to examine the energy behaviors at the sources and the superposed waves, separately. Both of the results reveal that the energy-doubling phenomenon presents when the dipoles are placed in close proximity. As the distance between the two dipoles increases, it is found that the total radiative power fluctuates in a damped manner and ultimately converges to a value required by energy conservation law. The theoretical conclusion of energy doubling is validated by experimental observations, which show a 1.59-fold increase in power within a microwave anechoic chamber. By analyzing the interactions, i.e., the EM coupling, between the two sources, we characterize a complete phenomenon of energy non-conservation.

physics.class-ph↗

arXiv2025

Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art deep learning model for representation learning on graphs. However, it remains notoriously challenging to train and inference GCNs over large graph datasets, limiting their application to large real-world graphs and hindering the exploration of deeper and more sophisticated GCN graphs. This is because as the graph size grows, the sheer number of node features and the large adjacency matrix can easily explode the required memory and data movements. To tackle the aforementioned challenges, we explore the possibility of drawing lottery tickets when sparsifying GCN graphs, i.e., subgraphs that largely shrink the adjacency matrix yet are capable of achieving accuracy comparable to or even better than their full graphs. Specifically, we for the first time discover the existence of graph early-bird (GEB) tickets that emerge at the very early stage when sparsifying GCN graphs, and propose a simple yet effective detector to automatically identify the emergence of such GEB tickets. Furthermore, we advocate graph-model co-optimization and develop a generic efficient GCN early-bird training framework dubbed GEBT that can significantly boost the efficiency of GCN training by (1) drawing joint early-bird tickets between the GCN graphs and models and (2) enabling simultaneously sparsification of both the GCN graphs and models. Experiments on various GCN models and datasets consistently validate our GEB finding and the effectiveness of our GEBT, e.g., our GEBT achieves up to 80.2% ~ 85.6% and 84.6% ~ 87.5% savings of GCN training and inference costs while offering a comparable or even better accuracy as compared to state-of-the-art methods. Our source code and supplementary appendix are available at https://github.com/RICE-EIC/Early-Bird-GCN.

cs.LG↗

arXiv2025

Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism

Binary Spiking Neural Networks (BSNNs) inherit the eventdriven paradigm of SNNs, while also adopting the reduced storage burden of binarization techniques. These distinct advantages grant BSNNs lightweight and energy-efficient characteristics, rendering them ideal for deployment on resource-constrained edge devices. However, due to the binary synaptic weights and non-differentiable spike function, effectively training BSNNs remains an open question. In this paper, we conduct an in-depth analysis of the challenge for BSNN learning, namely the frequent weight sign flipping problem. To mitigate this issue, we propose an Adaptive Gradient Modulation Mechanism (AGMM), which is designed to reduce the frequency of weight sign flipping by adaptively adjusting the gradients during the learning process. The proposed AGMM can enable BSNNs to achieve faster convergence speed and higher accuracy, effectively narrowing the gap between BSNNs and their full-precision equivalents. We validate AGMM on both static and neuromorphic datasets, and results indicate that it achieves state-of-the-art results among BSNNs. This work substantially reduces storage demands and enhances SNNs' inherent energy efficiency, making them highly feasible for resource-constrained environments.

cs.CV↗

arXiv2025

On the material genome of wurtzite ferroelectrics

As the dielectric film thickness shrinks to ~10 nm, some traditional wurtzite piezoelectric materials demonstrate ferroelectricity through element doping. Among them, Sc doped AlN and Mg doped ZnO are the most famous examples. While it is widely acknowledged that the dopant atoms effectively reduce the coercive field, enabling ferroelectric polarization switching, the material genome of these wurtzite (WZ) ferroelectrics is still less understood. In this work, we analyze the features of WZ ferroelectrics, ascribing them to five-coordination (5C) ferroelectrics, which may be compared with 6C ferroelectrics (perovskite-type) and 7C ferroelectrics (hafnia-like). In particular, the exact reason for their adopting the hexagonal WZ structure instead of the zinc blende structure is studied. Emphasis is paid to the degree of ionicity in promoting the hexagonal arrangement, and the phenomenon of layer distance compression is discovered and explained in WZ ferroelectrics. The role of element doping in coercive field reduction is understood within this context.

cond-mat.mtrl-sci↗

arXiv2024

Movable Antenna-Aided Secure Full-Duplex Multi-User Communications

In this paper, we investigate physical layer security (PLS) for full-duplex (FD) multi-user systems. We consider a base station (BS) that operates in FD mode and transmits artificial noise (AN) to simultaneously protect uplink (UL) and downlink (DL) transmissions. Conventional fixed-position antennas (FPAs) at the FD BS struggle to fully exploit spatial degrees of freedom (DoFs) to improve signal reception and suppress interference. To overcome this limitation, we propose a novel FD BS architecture equipped with multiple transmit and receive movable antennas (MAs). The MAs introduce the DoFs in antenna position optimization, which can improve the performance of secure communication systems. To serve users and counter the cooperative interception of multiple eavesdroppers (Eves), we formulate a sum of secrecy rates (SSR) maximization problem to jointly optimize the MA positions, the transmit, receive, and AN beamformers at the BS, and the UL powers. We propose an alternating optimization (AO) algorithm, which decomposes the original problem into three sub-problems, to solve the challenging non-convex optimization problem with highly coupled variables. Specifically, we propose the multi-velocity particle swarm optimization (MVPSO), which is an improved version of the standard particle swarm optimization (PSO), to simultaneously optimize all MA positions. The transmit/AN beamformers and the UL powers are solved by successive convex approximation (SCA). The optimal receive beamformer is derived as a closed-form solution. Simulation results demonstrate the effectiveness of the proposed algorithms and the advantages of MAs over conventional FPAs in enhancing the security of FD multi-user systems.

eess.SP↗

arXiv2024

Data value estimation on private gradients

For gradient-based machine learning (ML) methods commonly adopted in practice such as stochastic gradient descent, the de facto differential privacy (DP) technique is perturbing the gradients with random Gaussian noise. Data valuation attributes the ML performance to the training data and is widely used in privacy-aware applications that require enforcing DP such as data pricing, collaborative ML, and federated learning (FL). Can existing data valuation methods still be used when DP is enforced via gradient perturbations? We show that the answer is no with the default approach of injecting i.i.d.~random noise to the gradients because the estimation uncertainty of the data value estimation paradoxically linearly scales with more estimation budget, producing estimates almost like random guesses. To address this issue, we propose to instead inject carefully correlated noise to provably remove the linear scaling of estimation uncertainty w.r.t.~the budget. We also empirically demonstrate that our method gives better data value estimates on various ML tasks and is applicable to use cases including dataset valuation and~FL.

cs.LG↗

arXiv2024

Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer

Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase training scheme, involving base class pre-training followed by novel class fine-tuning, to learn the classifiers for base and novel classes respectively. Nevertheless, distribution gap exists between base and novel classes in this process. To narrow this gap, we exploit effective knowledge transfer from base to novel classes. First, a novel prototype modulation module is designed to modulate novel class prototypes by exploiting the correlations between base and novel classes. Second, a novel classifier calibration module is proposed to calibrate the weight distribution of the novel classifier according to that of the base classifier. Furthermore, existing GFSS approaches suffer from a lack of contextual information for novel classes due to their limited samples, we thereby introduce a context consistency learning scheme to transfer the contextual knowledge from base to novel classes. Extensive experiments on PASCAL-5$^i$ and COCO-20$^i$ demonstrate that our approach significantly enhances the state of the art in the GFSS setting. The code is available at: https://github.com/HHHHedy/GFSS-EKT.

cs.CV↗

arXiv2024

Power-Efficient Full-Duplex Satellite Communications Aided by Movable Antennas

This letter investigates a movable antenna (MA)-aided full-duplex (FD) satellite communication system, where the satellite, equipped with both transmit and receive MAs, serves multiple uplink (UL) and downlink (DL) user terminals (UTs) in FD mode. Specifically, we formulate a multiobjective optimization problem to minimize the UL and DL transmit powers under imperfect channel state information (CSI). To jointly optimize the MA positions and transmit powers, we propose a two-loop particle swarm optimization (PSO) algorithm based on a multiobjective optimization framework. Simulation results show that flexible adjustments of MA positions can effectively reduce the total UL and DL transmit powers, while also alleviating the burden on self-interference (SI) cancellation modules.

eess.SP↗

arXiv2024

DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning

In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without updating their parameters, significantly boosting their flexibility and generality. ICL possesses many distinct characteristics from conventional machine learning, thereby requiring new approaches to interpret this learning paradigm. Taking the viewpoint of recent works showing that transformers learn in context by formulating an internal optimizer, we propose an influence function-based attribution technique, DETAIL, that addresses the specific characteristics of ICL. We empirically verify the effectiveness of our approach for demonstration attribution while being computationally efficient. Leveraging the results, we then show how DETAIL can help improve model performance in real-world scenarios through demonstration reordering and curation. Finally, we experimentally prove the wide applicability of DETAIL by showing our attribution scores obtained on white-box models are transferable to black-box models in improving model performance.

cs.CL↗

arXiv2024

Learning Flow Fields in Attention for Controllable Person Image Generation

Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person's appearance or pose. However, prior methods often distort fine-grained textural details from the reference image, despite achieving high overall image quality. We attribute these distortions to inadequate attention to corresponding regions in the reference image. To address this, we thereby propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key in the attention layer during training. Specifically, it is realized via a regularization loss on top of the attention map within a diffusion-based baseline. Our extensive experiments show that Leffa achieves state-of-the-art performance in controlling appearance (virtual try-on) and pose (pose transfer), significantly reducing fine-grained detail distortion while maintaining high image quality. Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models.

cs.CV↗

arXiv2024

Is the neural tangent kernel of PINNs deep learning general partial differential equations always convergent ?

In this paper, we study the neural tangent kernel (NTK) for general partial differential equations (PDEs) based on physics-informed neural networks (PINNs). As we all know, the training of an artificial neural network can be converted to the evolution of NTK. We analyze the initialization of NTK and the convergence conditions of NTK during training for general PDEs. The theoretical results show that the homogeneity of differential operators plays a crucial role for the convergence of NTK. Moreover, based on the PINNs, we validate the convergence conditions of NTK using the initial value problems of the sine-Gordon equation and the initial-boundary value problem of the KdV equation.

stat.ML↗

arXiv2024

Coding Over Coupon Collector Channels for Combinatorial Motif-Based DNA Storage

Encoding information in combinations of pre-synthesised deoxyribonucleic acid (DNA) strands (referred to as motifs) is an interesting approach to DNA storage that could potentially circumvent the prohibitive costs of nucleotide-by-nucleotide DNA synthesis. Based on our analysis of an empirical data set from HelixWorks, we propose two channel models for this setup (with and without interference) and analyse their fundamental limits. We propose a coding scheme that approaches those limits by leveraging all information available at the output of the channel, in contrast to earlier schemes developed for a similar setup by Preuss et al. We highlight an important connection between channel capacity curves and the fundamental trade-off between synthesis (writing) and sequencing (reading), and offer a way to mitigate an exponential growth in decoding complexity with the size of the motif library.

cs.IT↗

arXiv2024

Near-Field Multiuser Communications Aided by Movable Antennas

This letter investigates movable antenna (MA)-aided downlink (DL) multiuser communication systems under the near-field channel condition, where both the base station (BS) and the users are equipped with MAs to fully exploit the degrees of freedom (DoFs) in antenna position optimization. We develop a general channel model to accurately describe the channel characteristics in the near-field region and formulate an MA-position optimization problem to minimize the BS's transmit power subject to users' individual rate constraints. To solve this problem, we propose a two-loop dynamic neighborhood pruning particle swarm optimization (DNPPSO) algorithm that significantly reduces the computational complexity as compared to the standard particle swarm optimization (PSO) algorithm while achieving similar performance. Simulation results validate the effectiveness and advantages of the proposed scheme in power-saving for near-field multiuser communications.

eess.SP↗

arXiv2024

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in an asymmetric network design: i) a MAR-based planning model containing most of the parameters generates planning signals for each masked frame using low-resolution input; ii) a lightweight generation model uses these signals to produce high-resolution frames via diffusion de-noising. MarDini's MAR enables video generation conditioned on any number of masked frames at any frame positions: a single model can handle video interpolation (e.g., masking middle frames), image-to-video generation (e.g., masking from the second frame onward), and video expansion (e.g., masking half the frames). The efficient design allocates most of the computational resources to the low-resolution planning model, making computationally expensive but important spatio-temporal attention feasible at scale. MarDini sets a new state-of-the-art for video interpolation; meanwhile, within few inference steps, it efficiently generates videos on par with those of much more expensive advanced image-to-video models.

cs.CV↗

arXiv2024

Prototype of Secure Wire-Line Telephone

This paper presents a secure wire-line telephone system that employs physical layer security (PLS) to protect against wiretapping. The system generates artificial noise (AN) in both transmission directions and uses a telephone hybrid circuit to effectively suppress the AN for the purpose of secure communication. Furthermore, we analyze the secrecy capacity of the system and evaluate its performance through theoretical analysis and practical experiments. The results demonstrate that the proposed system can significantly enhance communication security while preserving the integrity of legitimate signals. The results also validate that the proposed system is a robust and effective solution for securing wire-line telephone communications.

eess.SP↗

arXiv2024

Oriented Supersingular Elliptic Curves and Eichler Orders

Let $p>3$ be a prime and $E$ be a supersingular elliptic curve defined over $\mathbb{F}_{p^2}$. Let $c$ be a prime with $c < 3p/16$ and $G$ be a subgroup of $E[c]$ of order $c$. The pair $(E,G)$ is called a supersingular elliptic curve with level-$c$ structure, and the endomorphism ring $\text{End}(E,G)$ is isomorphic to an Eichler order with level $c$. We construct two kinds of Eichler orders $\mathcal{O}_c(q,r)$ and $\mathcal{O}'_c(q,r')$ with level $c$. Interestingly, we prove that each $\mathcal{O}_c(q,r)$ or $\mathcal{O}'_c(q,r')$ can represent a primitive reduced binary quadratic form with discriminant $-16cp$ or $-cp$ respectively. If a curve $E$ is $\mathbb{Z}[\sqrt{-cp}]$-oriented or $\mathbb{Z}[\frac{1+\sqrt{-cp}}{2}]$-oriented, then we prove that $\text{End}(E,G)$ is isomorphic to $\mathcal{O}_c(q,r)$ or $\mathcal{O}'_c(q,r')$ respectively. Due to the fact that $\mathbb{Z}[\sqrt{-cp}]$-oriented isogenies between $\mathbb{Z}[\sqrt{-cp}]$-oriented elliptic curves could be represented by quadratic forms, we show that these isogenies are reflected in the corresponding Eichler orders via the composition law for their corresponding quadratic forms.

math.NT↗

arXiv2024

Secure Full-Duplex Communication via Movable Antennas

This paper investigates physical layer security (PLS) in a movable antenna (MA)-assisted full-duplex (FD) system. In this system, an FD base station (BS) with multiple MAs for transmission and reception provides services for an uplink (UL) user and a downlink (DL) user. Each user operates in half-duplex (HD) mode and is equipped with a single fixed-position antenna (FPA), in the presence of a single-FPA eavesdropper (Eve). To ensure secure communication, artificial noise (AN) is transmitted to obstruct the interception of Eve. The objective of this paper is to maximize the sum secrecy rate (SSR) of the UL and DL users by jointly optimizing the beamformers of the BS and the positions of MAs. This paper also proposes an alternating optimization (AO) method to address the non-convex problem, which decomposes the optimization problem into three subproblems and solves them iteratively. Simulation results demonstrate a significant performance gain in the SSR achieved by the proposed scheme compared to the benchmark schemes.

cs.IT↗

arXiv2024

Movable Antenna-Enabled Co-Frequency Co-Time Full-Duplex Wireless Communication

Movable antenna (MA) provides an innovative way to arrange antennas that can contribute to improved signal quality and more effective interference management. This technology is especially beneficial for co-frequency co-time full-duplex (CCFD) wireless communication, which struggles with self-interference (SI) that usually overpowers the desired incoming signals. By dynamically repositioning transmit/receive antennas, we can mitigate the SI and enhance the reception of incoming signals. Thus, this paper proposes a novel MA-enabled point-to-point CCFD system and formulates the minimum achievable rate of two CCFD terminals. To maximize the minimum achievable rate and determine the positions of MAs, we introduce a solution based on projected particle swarm optimization (PPSO), which can circumvent common suboptimal positioning issues. Moreover, simulation results reveal that the PPSO method leads to better performance compared to the conventional alternating position optimization (APO). The results also demonstrate that an MA-enabled CCFD system outperforms the one using fixed-position antennas (FPAs).

cs.IT↗