Searcharxiv⌕ Search

arXiv subjects

Xuan Zhang

Publications and source records attributed to Xuan Zhang.

At least 127 records · Page 7Linked to original sources
arXiv2024

Enhancing Continuous Domain Adaptation with Multi-Path Transfer Curriculum

Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuous Domain Adaptation (CDA) has emerged as an effective technique, closing this gap by utilizing a series of intermediate domains. This paper contributes a novel CDA method, W-MPOT, which rigorously addresses the domain ordering and error accumulation problems overlooked by previous studies. Specifically, we construct a transfer curriculum over the source and intermediate domains based on Wasserstein distance, motivated by theoretical analysis of CDA. Then we transfer the source model to the target domain through multiple valid paths in the curriculum using a modified version of continuous optimal transport. A bidirectional path consistency constraint is introduced to mitigate the impact of accumulated mapping errors during continuous transfer. We extensively evaluate W-MPOT on multiple datasets, achieving up to 54.1\% accuracy improvement on multi-session Alzheimer MR image classification and 94.7\% MSE reduction on battery capacity estimation.

cs.LG↗
arXiv2024

A New Testing Method for Justification Bias Using High-Frequency Data of Health and Employment

Justification bias, wherein retirees may report poorer health to rationalize their retirement, poses a major concern to the widely-used measure of self-assessed health in retirement studies. This paper introduces a novel method for testing the presence of this bias in the spirit of regression discontinuity. The underlying idea is that any sudden shift in self-assessed health immediately following retirement is more likely attributable to the bias. Our strategy is facilitated by a unique high-frequency data that offers monthly, in contrast to the typical biennial, information on employment, self-assessed health, and objective health conditions. Across a wider post-retirement time frame, we observe a decline in self-assessed health, potentially stemming from both justification bias and changes in actual health. However, this adverse effect diminishes with shorter intervals, indicating no evidence of such bias. Our method also validates a widely-used indirect testing approach.

econ.GN↗
arXiv2024

Closed-loop control of gamma oscillations in the brain connections through the transcranial stimulations

The reconstruction of brain neural network connections occurs not only during the infancy and early childhood stages of brain development, but also in patients with cognitive impairment in middle and old age under the therapy with stimulated external interference, such as the non-invasive repetitive transcranial magnetic stimulation (rTMS) and the transcranial direct current stimulation(tDCS). However, until now, it is not clear how brain stimulation triggers and controls the reconstruction of neural network connections in the brain. This paper combines the EEG data analysis and the cortical neuronal network modeling methods. On one hand, an E-I balanced cortical neural network model was constructed under a long-lasting external stimulation of sinusoidal-exponential form TMS or square-wave tDCS was introduced into the network model for simulate the treatment process for the brain connections. On the other hand, by combining Butterworth filter and functional connectivity algorithm, the paper analyzes the relations between the attentional gamma oscillation responses and the brain connection based on the publicly available EEGs during the pre-tDCS and post-tDCS treatment phases. Firstly, the simulation results indicate that, during long-lasting external stimulations of tDCS/rTMS, The sustained gamma oscillation was found to trigger more release of BDNF from astrocytes to participate in the positively reshaping the excitatory neuronal network connection.

q-bio.NC↗
arXiv2024

Realization of the Non-endpoint Majorana Bound States in an Extended Kitaev Chain

We study the energy levels and transport properties of an extended Kitaev chain with a phase gradient. It is demonstrated that the hopping phase difference can effectively induce the generation of Majorana bound states, which are located at the non-endpoint sites of the chain. The number and positions of the non-endpoint Majorana bound states can be modulated by the hopping phase difference and initial hopping phase, respectively. In addition, we propose a protocol to realize topological braiding operation by exchanging the positions of two Majorana bound states in the extended Kitaev ring. Furthermore, we also implement the braiding of any two of the multiple Majorana bound states in the extended Kitaev double rings.

cond-mat.mes-hall↗
arXiv2024

On the Multi-turn Instruction Following for Conversational Web Agents

Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the context-dependency issue of the conversational tasks, we further propose a novel framework, named self-reflective memory-augmented planning (Self-MAP), which employs memory utilization and self-reflection techniques. Extensive experiments are conducted to benchmark the MT-Mind2Web dataset, and validate the effectiveness of the proposed method.

cs.CL↗
arXiv2024

Simulation Studies for the First Pathfinder of the CATCH Space Mission

The Chasing All Transients Constellation Hunters (CATCH) space mission is an intelligent constellation consisting of 126 micro-satellites in three types (A, B, and C), designed for X-ray observation with the objective of studying the dynamic universe. Currently, we are actively developing the first Pathfinder (CATCH-1) for the CATCH mission, specifically for type-A satellites. CATCH-1 is equipped with Micro Pore Optics (MPO) and a 4-pixel Silicon Drift Detector (SDD) array. To assess its scientific performance, including the effective area of the optical system, on-orbit background, and telescope sensitivity, we employ the Monte Carlo software Geant4 for simulation in this study. The MPO optics exhibit an effective area of $41$ cm$^2$ at the focal spot for 1 keV X-rays, while the entire telescope system achieves an effective area of $29$ cm$^2$ at 1 keV when taking into account the SDD detector's detection efficiency. The primary contribution to the background is found to be from the Cosmic X-ray Background. Assuming a 625 km orbit with an inclination of $29^\circ$, the total background for CATCH-1 is estimated to be $8.13\times10^{-2}$ counts s$^{-1}$ in the energy range of 0.5--4 keV. Based on the background within the central detector and assuming a Crab-like source spectrum, the estimated ideal sensitivity could achieve $1.9\times10^{-12}$ erg cm$^{-2}$ s$^{-1}$ for an exposure of 10$^4$ s in the energy band of 0.5--4 keV. Furthermore, after simulating the background caused by low-energy charged particles near the geomagnetic equator, we have determined that there is no need to install a magnetic deflector.

astro-ph.IM↗
arXiv2024

CktGNN: Circuit Graph Neural Network for Electronic Design Automation

The electronic design automation of analog circuits has been a longstanding challenge in the integrated circuit field due to the huge design space and complex design trade-offs among circuit specifications. In the past decades, intensive research efforts have mostly been paid to automate the transistor sizing with a given circuit topology. By recognizing the graph nature of circuits, this paper presents a Circuit Graph Neural Network (CktGNN) that simultaneously automates the circuit topology generation and device sizing based on the encoder-dependent optimization subroutines. Particularly, CktGNN encodes circuit graphs using a two-level GNN framework (of nested GNN) where circuits are represented as combinations of subgraphs in a known subgraph basis. In this way, it significantly improves design efficiency by reducing the number of subgraphs to perform message passing. Nonetheless, another critical roadblock to advancing learning-assisted circuit design automation is a lack of public benchmarks to perform canonical assessment and reproducible research. To tackle the challenge, we introduce Open Circuit Benchmark (OCB), an open-sourced dataset that contains $10$K distinct operational amplifiers with carefully-extracted circuit specifications. OCB is also equipped with communicative circuit generation and evaluation capabilities such that it can help to generalize CktGNN to design various analog circuits by producing corresponding datasets. Experiments on OCB show the extraordinary advantages of CktGNN through representation-based optimization frameworks over other recent powerful GNN baselines and human experts' manual designs. Our work paves the way toward a learning-based open-sourced design automation for analog circuits. Our source code is available at \url{https://github.com/zehao-dong/CktGNN}.

cs.LG↗
arXiv2024

SATac: A Thermoluminescence Enabled Tactile Sensor for Concurrent Perception of Temperature, Pressure, and Shear

Most vision-based tactile sensors use elastomer deformation to infer tactile information, which can not sense some modalities, like temperature. As an important part of human tactile perception, temperature sensing can help robots better interact with the environment. In this work, we propose a novel multimodal vision-based tactile sensor, SATac, which can simultaneously perceive information of temperature, pressure, and shear. SATac utilizes thermoluminescence of strontium aluminate (SA) to sense a wide range of temperatures with exceptional resolution. Additionally, the pressure and shear can also be perceived by analyzing Voronoi diagram. A series of experiments are conducted to verify the performance of our proposed sensor. We also discuss the possible application scenarios and demonstrate how SATac could benefit robot perception capabilities.

cs.RO↗
arXiv2024

Hardware Phi-1.5B: A Large Language Model Encodes Hardware Domain Specific Knowledge

In the rapidly evolving semiconductor industry, where research, design, verification, and manufacturing are intricately linked, the potential of Large Language Models to revolutionize hardware design and security verification is immense. The primary challenge, however, lies in the complexity of hardware specific issues that are not adequately addressed by the natural language or software code knowledge typically acquired during the pretraining stage. Additionally, the scarcity of datasets specific to the hardware domain poses a significant hurdle in developing a foundational model. Addressing these challenges, this paper introduces Hardware Phi 1.5B, an innovative large language model specifically tailored for the hardware domain of the semiconductor industry. We have developed a specialized, tiered dataset comprising small, medium, and large subsets and focused our efforts on pretraining using the medium dataset. This approach harnesses the compact yet efficient architecture of the Phi 1.5B model. The creation of this first pretrained, hardware domain specific large language model marks a significant advancement, offering improved performance in hardware design and verification tasks and illustrating a promising path forward for AI applications in the semiconductor sector.

cs.CL↗
arXiv2024

Predicting Viral Rumors and Vulnerable Users for Infodemic Surveillance

In the age of the infodemic, it is crucial to have tools for effectively monitoring the spread of rampant rumors that can quickly go viral, as well as identifying vulnerable users who may be more susceptible to spreading such misinformation. This proactive approach allows for timely preventive measures to be taken, mitigating the negative impact of false information on society. We propose a novel approach to predict viral rumors and vulnerable users using a unified graph neural network model. We pre-train network-based user embeddings and leverage a cross-attention mechanism between users and posts, together with a community-enhanced vulnerability propagation (CVP) method to improve user and propagation graph representations. Furthermore, we employ two multi-task training strategies to mitigate negative transfer effects among tasks in different settings, enhancing the overall performance of our approach. We also construct two datasets with ground-truth annotations on information virality and user vulnerability in rumor and non-rumor events, which are automatically derived from existing rumor detection datasets. Extensive evaluation results of our joint learning model confirm its superiority over strong baselines in all three tasks: rumor detection, virality prediction, and user vulnerability scoring. For instance, compared to the best baselines based on the Weibo dataset, our model makes 3.8\% and 3.0\% improvements on Accuracy and MacF1 for rumor detection, and reduces mean squared error (MSE) by 23.9\% and 16.5\% for virality prediction and user vulnerability scoring, respectively. Our findings suggest that our approach effectively captures the correlation between rumor virality and user vulnerability, leveraging this information to improve prediction performance and provide a valuable tool for infodemic surveillance.

cs.SI↗
arXiv2023

Multi-Satellite Cooperative Networks: Joint Hybrid Beamforming and User Scheduling Design

In this paper, we consider a cooperative communication network where multiple low-Earth-orbit (LEO) satellites provide services to multiple ground users (GUs) cooperatively at the same time and on the same frequency. The multi-satellite cooperation has great potential in extending communication coverage and increasing spectral efficiency. Considering that the on-board radio-frequency circuit resources and computation resources on each satellite are restricted, we aim to propose a low-complexity yet efficient multi-satellite cooperative transmission framework. Specifically, we first propose a hybrid beamforming method consisting of analog beamforming for beam alignment and digital beamforming for interference mitigation. Then, to establish appropriate connections between the satellites and GUs, we propose a heuristic user scheduling algorithm which determines the connections according to the total spectral efficiency increment of the multi-satellite cooperative network. Next, considering the intrinsic connection between beamforming and user scheduling, a joint hybrid beamforming and user scheduling (JHU) scheme is proposed to dramatically improve the performance of the multi-satellite cooperative network. In addition to the single-connection scenario, we also consider the multi-connection case using the JHU scheme. Extensive simulations conducted over different LEO satellite constellations and across various GU locations demonstrate the superiority of the proposed schemes in both overall and per-user spectral efficiencies.

cs.IT↗
arXiv2023

Learning Neural Traffic Rules

Extensive research has been devoted to the field of multi-agent navigation. Recently, there has been remarkable progress attributed to the emergence of learning-based techniques with substantially elevated intelligence and realism. Nonetheless, prevailing learned models face limitations in terms of scalability and effectiveness, primarily due to their agent-centric nature, i.e., the learned neural policy is individually deployed on each agent. Inspired by the efficiency observed in real-world traffic networks, we present an environment-centric navigation policy. Our method learns a set of traffic rules to coordinate a vast group of unintelligent agents that possess only basic collision-avoidance capabilities. Our method segments the environment into distinct blocks and parameterizes the traffic rule using a Graph Recurrent Neural Network (GRNN) over the block network. Each GRNN node is trained to modulate the velocities of agents as they traverse through. Using either Imitation Learning (IL) or Reinforcement Learning (RL) schemes, we demonstrate the efficacy of our neural traffic rules in resolving agent congestion, closely resembling real-world traffic regulations. Our method handles up to $240$ agents at real-time and generalizes across diverse agent and environment configurations.

cs.RO↗
arXiv2023

Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method

While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still under-explored in the misinformation domain. In this paper, we examine LLMs with in-context learning (ICL) for news claim verification, and find that only with 4-shot demonstration examples, the performance of several prompting methods can be comparable with previous supervised models. To further boost performance, we introduce a Hierarchical Step-by-Step (HiSS) prompting method which directs LLMs to separate a claim into several subclaims and then verify each of them via multiple questions-answering steps progressively. Experiment results on two public misinformation datasets show that HiSS prompting outperforms state-of-the-art fully-supervised approach and strong few-shot ICL-enabled baselines.

cs.CL↗
arXiv2023

GNNHLS: Evaluating Graph Neural Network Inference via High-Level Synthesis

With the ever-growing popularity of Graph Neural Networks (GNNs), efficient GNN inference is gaining tremendous attention. Field-Programming Gate Arrays (FPGAs) are a promising execution platform due to their fine-grained parallelism, low-power consumption, reconfigurability, and concurrent execution. Even better, High-Level Synthesis (HLS) tools bridge the gap between the non-trivial FPGA development efforts and rapid emergence of new GNN models. In this paper, we propose GNNHLS, an open-source framework to comprehensively evaluate GNN inference acceleration on FPGAs via HLS, containing a software stack for data generation and baseline deployment, and FPGA implementations of 6 well-tuned GNN HLS kernels. We evaluate GNNHLS on 4 graph datasets with distinct topologies and scales. The results show that GNNHLS achieves up to 50.8x speedup and 423x energy reduction relative to the CPU baselines. Compared with the GPU baselines, GNNHLS achieves up to 5.16x speedup and 74.5x energy reduction.

cs.LG↗
arXiv2023

Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning

A set of variables is the Markov blanket of a random variable if it contains all the information needed for predicting the variable. If the blanket cannot be reduced without losing useful information, it is called a Markov boundary. Identifying the Markov boundary of a random variable is advantageous because all variables outside the boundary are superfluous. Hence, the Markov boundary provides an optimal feature set. However, learning the Markov boundary from data is challenging for two reasons. If one or more variables are removed from the Markov boundary, variables outside the boundary may start providing information. Conversely, variables within the boundary may stop providing information. The true role of each candidate variable is only manifesting when the Markov boundary has been identified. In this paper, we propose a new Tsetlin Machine (TM) feedback scheme that supplements Type I and Type II feedback. The scheme introduces a novel Finite State Automaton - a Context-Specific Independence Automaton. The automaton learns which features are outside the Markov boundary of the target, allowing them to be pruned from the TM during learning. We investigate the new scheme empirically, showing how it is capable of exploiting context-specific independence to find Markov boundaries. Further, we provide a theoretical analysis of convergence. Our approach thus connects the field of Bayesian networks (BN) with TMs, potentially opening up for synergies when it comes to inference and learning, including TM-produced Bayesian knowledge bases and TM-based Bayesian inference.

cs.LG↗
arXiv2023

Fairness-aware Online Price Discrimination with Nonparametric Demand Models

Price discrimination, which refers to the strategy of setting different prices for different customer groups, has been widely used in online retailing. Although it helps boost the collected revenue for online retailers, it might create serious concerns about fairness, which even violates the regulation and laws. This paper studies the problem of dynamic discriminatory pricing under fairness constraints. In particular, we consider a finite selling horizon of length $T$ for a single product with two groups of customers. Each group of customers has its unknown demand function that needs to be learned. For each selling period, the seller determines the price for each group and observes their purchase behavior. While existing literature mainly focuses on maximizing revenue, ensuring fairness among different customers has not been fully explored in the dynamic pricing literature. This work adopts the fairness notion from Cohen et al. (2022). For price fairness, we propose an optimal dynamic pricing policy regarding regret, which enforces the strict price fairness constraint. In contrast to the standard $\sqrt{T}$-type regret in online learning, we show that the optimal regret in our case is $\tilde{O}(T^{4/5})$. We further extend our algorithm to a more general notion of fairness, which includes demand fairness as a special case. To handle this general class, we propose a soft fairness constraint and develop a dynamic pricing policy that achieves $\tilde{O}(T^{4/5})$ regret. We also demonstrate that our algorithmic techniques can be adapted to more general scenarios such as fairness among multiple groups of customers.

cs.LG↗
arXiv2023

Group Equivariant Fourier Neural Operators for Partial Differential Equations

We consider solving partial differential equations (PDEs) with Fourier neural operators (FNOs), which operate in the frequency domain. Since the laws of physics do not depend on the coordinate system used to describe them, it is desirable to encode such symmetries in the neural operator architecture for better performance and easier learning. While encoding symmetries in the physical domain using group theory has been studied extensively, how to capture symmetries in the frequency domain is under-explored. In this work, we extend group convolutions to the frequency domain and design Fourier layers that are equivariant to rotations, translations, and reflections by leveraging the equivariance property of the Fourier transform. The resulting $G$-FNO architecture generalizes well across input resolutions and performs well in settings with varying levels of symmetry. Our code is publicly available as part of the AIRS library (https://github.com/divelab/AIRS).

cs.LG↗
arXiv2023

Photometric calibration of the Stellar Abundance and Galactic Evolution Survey (SAGES): Nanshan One-meter Wide-field Telescope g, r, and i band imaging data

In this paper, a total of approximately 2.6 million dwarfs were constructed as standard stars, with an accuracy of about 0.01-0.02 mag for each band, by combining spectroscopic data from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope Data Release 7, photometric data from the corrected Gaia Early Data Release 3, and photometric metallicities. Using the spectroscopy based stellar color regression method (SCR method) and the photometric-based SCR method (SCR' method), we performed the relative calibration of the Nanshan One-meter Wide-field Telescope imaging data. Based on the corrected Pan-STARRS DR1 photometry, the absolute calibration was also performed. In the photometric calibration process, we analyzed the dependence of the calibration zero points on different images (observation time), different gates of the CCD detector, and different CCD positions. We found that the stellar flat and the relative gain between different gates depend on time. The amplitude of gain variation in three channels is approximately 0.5%-0.7% relative to the other channel, with a maximum value of 4%. In addition, significant spatial variations of the stellar flat fitting residual are found and corrected. Using repeated sources in the adjacent images, we checked and discovered internal consistency of about 1-2 mmag in all the filters. Using the PS1 magnitudes synthesized by Gaia DR3 BP/RP spectra by the synthetic photometry method, we found that the photometric calibration uniformity is about 1-2 mmag for all the bands, at a spatial resolution of 1.3 degree. A detailed comparison between the spectroscopy-based SCR and photometric-based SCR method magnitude offsets was performed, and we achieved an internal consistency precision of about 2 mmag or better with resolutions of 1.3 degree for all the filters. Which is mainly from the position-dependent errors of the E(B-V) used in SCR' method.

astro-ph.SR↗