Searcharxiv⌕ Search

arXiv subjects

Jun Zhao

Publications and source records attributed to Jun Zhao.

At least 307 records · Page 17Linked to original sources
arXiv2023

Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database

In Textual question answering (TQA) systems, complex questions often require retrieving multiple textual fact chains with multiple reasoning steps. While existing benchmarks are limited to single-chain or single-hop retrieval scenarios. In this paper, we propose to conduct Graph-Hop -- a novel multi-chains and multi-hops retrieval and reasoning paradigm in complex question answering. We construct a new benchmark called ReasonGraphQA, which provides explicit and fine-grained evidence graphs for complex questions to support interpretable reasoning, comprehensive and detailed reasoning. And ReasonGraphQA also shows an advantage in reasoning diversity and scale. Moreover, We propose a strong graph-hop baseline called Bidirectional Graph Retrieval (BGR) method for generating an explanation graph of textual evidence in knowledge reasoning and question answering. We have thoroughly evaluated existing evidence retrieval and reasoning models on the ReasonGraphQA. Experiments highlight Graph-Hop is a promising direction for answering complex questions, but it still has certain limitations. We have further studied mitigation strategies to meet these challenges and discuss future directions.

cs.CL↗
arXiv2023

User-centric Heterogeneous-action Deep Reinforcement Learning for Virtual Reality in the Metaverse over Wireless Networks

The Metaverse is emerging as maturing technologies are empowering the different facets. Virtual Reality (VR) technologies serve as the backbone of the virtual universe within the Metaverse to offer a highly immersive user experience. As mobility is emphasized in the Metaverse context, VR devices reduce their weights at the sacrifice of local computation abilities. In this paper, for a system consisting of a Metaverse server and multiple VR users, we consider two cases of (i) the server generating frames and transmitting them to users, and (ii) users generating frames locally and thus consuming device energy. Moreover, in our multi-user VR scenario for the Metaverse, users have different characteristics and demands for Frames Per Second (FPS). Then the channel access arrangement (including the decisions on frame generation location), and transmission powers for the downlink communications from the server to the users are jointly optimized to improve the utilities of users. This joint optimization is addressed by deep reinforcement learning (DRL) with heterogeneous actions. Our proposed user-centric DRL algorithm is called User-centric Critic with Heterogenous Actors (UCHA). Extensive experiments demonstrate that our UCHA algorithm leads to remarkable results under various requirements and constraints.

cs.NI↗
arXiv2023

Spin Fluctuations in Sr$_{1.8}$La$_{0.2}$RuO$_4$

We use inelastic neutron scattering to study spin fluctuations in Sr$_{1.8}$La$_{0.2}$RuO$_4$, where Lanthanum doping triggers a Lifshitz transition by pushing the van Hove singularity in the $γ$ band to the Fermi energy. Strong spin fluctuations emerge at an incommensurate wave vector $\mathbf{Q}_{ic} = (0.3,0.3)$, corresponding to the nesting vector between $α$ and $β$ Fermi sheets. The incommensurate antiferromagnetic fluctuations shift toward $(0.25,0.25)$ with increasing energy up to ${\sim}110$ meV. By contrast, scatterings near the ferromagnetic wave vectors $\mathbf{Q} = (1,0)$ and $(1,1)$ remain featureless at all energies. This contradicts the weak-coupling perspective that suggests a sharp enhancement of ferromagnetic susceptibility due to the divergence of density of states in the associated $γ$ band. Our findings imply that ferromagnetic fluctuations in Sr$_2$RuO$_4$ and related materials do not fit into the weak-coupling paradigm, but instead are quasi-local fluctuations induced by Hund's coupling. This imposes significant constraints for the pairing mechanism involving spin fluctuations.

cond-mat.str-el↗
arXiv2023

Large Language Models Need Holistically Thought in Medical Conversational QA

The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care. Despite the success of large language models (LLMs) in complex reasoning tasks in various fields, such as mathematics, logic, and commonsense QA, they still need to improve with the increased complexity and specialization of the medical field. This is because medical CQA tasks require not only strong medical reasoning, but also the ability to think broadly and deeply. In this paper, to address these challenges in medical CQA tasks that need to be considered and understood in many aspects, we propose the Holistically Thought (HoT) method, which is designed to guide the LLMs to perform the diffused and focused thinking for generating high-quality medical responses. The proposed HoT method has been evaluated through automated and manual assessments in three different medical CQA datasets containing the English and Chinese languages. The extensive experimental results show that our method can produce more correctness, professional, and considerate answers than several state-of-the-art (SOTA) methods, manifesting its effectiveness. Our code in https://github.com/WENGSYX/HoT.

cs.CL↗
arXiv2023

Utility-Oriented Wireless Communications for 6G Networks: Semantic Information Transfer for IRS aided Vehicular Metaverse

This paper introduces the novel utility-oriented communications (UOC) concept and identifies its importance for 6G wireless technology. UOC encompasses existing communication paradigms and includes emerging human-centric and task-oriented communications concepts. The authors investigate semantic communications and semantic information transfer for vehicular metaverse as a case study of UOC. Consider the Internet of Vehicles (IoV) users access real-time virtual world updates from the base station (BS) wirelessly using semantic communication, and an intelligent reflecting surface (IRS) is deployed to impair co-channel interference. This paper formulates an optimization problem where a novel utility expression for semantic communications is incorporated. The proposed system model jointly considers latency and power in wireless communication and the utility of semantic communication. The proposed alternative optimization algorithm balances system efficiency and economics and outperforms existing optimization algorithms under the same channel conditions.

cs.SI↗
arXiv2023

Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question

Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task. Existing methods based on encoder-decoder framework employ a expression tree-based decoder to solve numerical reasoning problems. However, encoders rely more on Machine Reading Comprehension (MRC) methods, which take table serialization and text splicing as input, damaging the granularity relationship between table and text as well as the spatial structure information of table itself. In order to solve these problems, the paper proposes a Multi-View Graph (MVG) Encoder to take the relations among the granularity into account and capture the relations from multiple view. By utilizing MVGE as a module, we constuct Tabular View, Relation View and Numerical View which aim to retain the original characteristics of the hybrid data. We validate our model on the publicly available table-text hybrid QA benchmark (TAT-QA) and outperform the state-of-the-art model.

cs.CL↗
arXiv2023

Semantic communications, semantic edge computing, and semantic caching

The increasing popularity of applications like the Metaverse has led to the exploration of new, more effective ways of communication. Semantic communication, which focuses on the meaning behind transmitted information, represents a departure from traditional communication paradigms. As mobile devices become increasingly prevalent, it is important to explore the potential of edge computing to aid the semantic encoding/decoding process, which requires significant computing power and storage capabilities. However, establishing knowledge bases (KBs) for domain-oriented communication can be time-consuming. To address this challenge, this paper proposes a semantic caching model in edge computing system that caches domain-specialized general models and user-specific individual models. This approach has the potential to reduce the time and resources required to establish individual KBs while accurately capturing the semantics behind users' messages, ultimately leading to more efficient and accessible semantic communication.

cs.SI↗
arXiv2023

Towards Adversarially Robust Continual Learning

Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real world. Deep learning models, however, are shown to be vulnerable to adversarial attacks. Though there are many studies on the model robustness in the context of standard supervised learning, protecting continual learning from adversarial attacks has not yet been investigated. To fill in this research gap, we are the first to study adversarial robustness in continual learning and propose a novel method called \textbf{T}ask-\textbf{A}ware \textbf{B}oundary \textbf{A}ugmentation (TABA) to boost the robustness of continual learning models. With extensive experiments on CIFAR-10 and CIFAR-100, we show the efficacy of adversarial training and TABA in defending adversarial attacks.

cs.LG↗
arXiv2023

Light higgsino scenario confronted with muon g-2

Light higgsinos below several hundred GeV are favored or required by the naturalness of low energy supersymmetry. If only higgsinos are light while other sparticles are sufficiently heavy, we have the so-called light higgsino scenario. Confronted with the muon $g-2$ data, this scenario is examined in this work. Since in this scenario the LSP (lightest sparticle) is higgsino-like, we need to also consider the dark matter constraints. Assuming a light higgsino mass parameter $μ$ in the range of 100-400 GeV while gaugino mass parameters above TeV, we explore the parameter space under the muon $g-2$ data and the dark matter constraints. We find that, to explain the muon $g-2$ anomaly at $2σ$, the winos and sleptons are respectively upper bounded by 3 TeV and 800 GeV. In this case, we find that the light higgsino-like dark matter can sizably scatter with nucleon and thus the allowed parameter space can be covered almost fully by the future LZ dark matter detection project. We also perform a Monte Carlo simulation to figure out the potential of HL-LHC to detect the light sleptons in this scenario. It turns out that compared with the current LHC limits, the HL-LHC can further cover a part of the parameter space.

hep-ph↗
arXiv2023

Mobile Edge Adversarial Detection for Digital Twinning to the Metaverse with Deep Reinforcement Learning

Real-time Digital Twinning of physical world scenes onto the Metaverse is necessary for a myriad of applications such as augmented-reality (AR) assisted driving. In AR assisted driving, physical environment scenes are first captured by Internet of Vehicles (IoVs) and are uploaded to the Metaverse. A central Metaverse Map Service Provider (MMSP) will aggregate information from all IoVs to develop a central Metaverse Map. Information from the Metaverse Map can then be downloaded into individual IoVs on demand and be delivered as AR scenes to the driver. However, the growing interest in developing AR assisted driving applications which relies on digital twinning invites adversaries. These adversaries may place physical adversarial patches on physical world objects such as cars, signboards, or on roads, seeking to contort the virtual world digital twin. Hence, there is a need to detect these physical world adversarial patches. Nevertheless, as real-time, accurate detection of adversarial patches is compute-intensive, these physical world scenes have to be offloaded to the Metaverse Map Base Stations (MMBS) for computation. Hence in our work, we considered an environment with moving Internet of Vehicles (IoV), uploading real-time physical world scenes to the MMBSs. We formulated a realistic joint variable optimization problem where the MMSPs' objective is to maximize adversarial patch detection mean average precision (mAP), while minimizing the computed AR scene up-link transmission latency and IoVs' up-link transmission idle count, through optimizing the IoV-MMBS allocation and IoV up-link scene resolution selection. We proposed a Heterogeneous Action Proximal Policy Optimization (HAPPO) (discrete-continuous) algorithm to tackle the proposed problem. Extensive experiments shows HAPPO outperforms baseline models when compared against key metrics.

cs.NI↗
arXiv2023

Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer

Development of defenses against physical world attacks such as adversarial patches is gaining traction within the research community. We contribute to the field of adversarial patch detection by introducing an uncertainty-based adversarial patch localizer which localizes adversarial patch on an image, permitting post-processing patch-avoidance or patch-reconstruction. We quantify our prediction uncertainties with the development of \textit{\textbf{D}etection of \textbf{U}ncertainties in the \textbf{E}xceedance of \textbf{T}hreshold} (DUET) algorithm. This algorithm provides a framework to ascertain confidence in the adversarial patch localization, which is essential for safety-sensitive applications such as self-driving cars and medical imaging. We conducted experiments on localizing adversarial patches and found our proposed DUET model outperforms baseline models. We then conduct further analyses on our choice of model priors and the adoption of Bayesian Neural Networks in different layers within our model architecture. We found that isometric gaussian priors in Bayesian Neural Networks are suitable for patch localization tasks and the presence of Bayesian layers in the earlier neural network blocks facilitates top-end localization performance, while Bayesian layers added in the later neural network blocks contribute to better model generalization. We then propose two different well-performing models to tackle different use cases.

cs.CV↗
arXiv2023

Optimizing Utility-Energy Efficiency for the Metaverse over Wireless Networks under Physical Layer Security

The Metaverse, an emerging digital space, is expected to offer various services mirroring the real world. Wireless communications for mobile Metaverse users should be tailored to meet the following user characteristics: 1) emphasizing application-specific perceptual utility instead of simply the transmission rate, 2) concerned with energy efficiency due to the limited device battery and energy intensiveness of some applications, and 3) caring about security as the applications may involve sensitive personal data. To this end, this paper incorporates application-specific utility, energy efficiency, and physical-layer security (PLS) into the studied optimization in a wireless network for the Metaverse. Specifically, after introducing utility-energy efficiency (UEE) to represent each Metaverse user's application-specific objective under PLS, we formulate an optimization to maximize the network's weighted sum-UEE by deciding users' transmission powers and communication bandwidths. The formulated problem belongs to the sum-of-ratios optimization, for which prior studies have demonstrated its difficulty. Nevertheless, our proposed algorithm 1) obtains the global optimum for the weighted sum-UEE optimization, via a transform to parametric convex optimization problems, 2) applies to any utility function which is concave, increasing, and twice differentiable, and 3) achieves a linear time complexity in the number of users (the optimal complexity in the order sense). Simulations confirm the superiority of our algorithm over other approaches. We explain that our technique for solving the sum-of-ratios optimization is applicable to other optimization problems in wireless networks and mobile computing.

cs.SI↗
arXiv2023

Resource Allocation of Federated Learning Assisted Mobile Augmented Reality System in the Metaverse

Metaverse has become a buzzword recently. Mobile augmented reality (MAR) is a promising approach to providing users with an immersive experience in the Metaverse. However, due to limitations of bandwidth, latency and computational resources, MAR cannot be applied on a large scale in the Metaverse yet. Moreover, federated learning, with its privacy-preserving characteristics, has emerged as a prospective distributed learning framework in the future Metaverse world. In this paper, we propose a federated learning assisted MAR system via non-orthogonal multiple access for the Metaverse. Additionally, to optimize a weighted sum of energy, latency and model accuracy, a resource allocation algorithm is devised by setting appropriate transmission power, CPU frequency and video frame resolution for each user. Experimental results demonstrate that our proposed algorithm achieves an overall good performance compared to a random algorithm and greedy algorithm.

cs.SI↗
arXiv2023

Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse over Wireless Communications

Technology advancements in wireless communications and high-performance Extended Reality (XR) have empowered the developments of the Metaverse. The demand for the Metaverse applications and hence, real-time digital twinning of real-world scenes is increasing. Nevertheless, the replication of 2D physical world images into 3D virtual objects is computationally intensive and requires computation offloading. The disparity in transmitted object dimension (2D as opposed to 3D) leads to asymmetric data sizes in uplink (UL) and downlink (DL). To ensure the reliability and low latency of the system, we consider an asynchronous joint UL-DL scenario where in the UL stage, the smaller data size of the physical world images captured by multiple extended reality users (XUs) will be uploaded to the Metaverse Console (MC) to be construed and rendered. In the DL stage, the larger-size 3D virtual objects need to be transmitted back to the XUs. We design a novel multi-agent reinforcement learning algorithm structure, namely Asynchronous Actors Hybrid Critic (AAHC), to optimize the decisions pertaining to computation offloading and channel assignment in the UL stage and optimize the DL transmission power in the DL stage. Extensive experiments demonstrate that compared to proposed baselines, AAHC obtains better solutions with satisfactory training time.

cs.LG↗
arXiv2023

Virtual Reality in Metaverse over Wireless Networks with User-centered Deep Reinforcement Learning

The Metaverse and its promises are fast becoming reality as maturing technologies are empowering the different facets. One of the highlights of the Metaverse is that it offers the possibility for highly immersive and interactive socialization. Virtual reality (VR) technologies are the backbone for the virtual universe within the Metaverse as they enable a hyper-realistic and immersive experience, and especially so in the context of socialization. As the virtual world 3D scenes to be rendered are of high resolution and frame rate, these scenes will be offloaded to an edge server for computation. Besides, the metaverse is user-center by design, and human users are always the core. In this work, we introduce a multi-user VR computation offloading over wireless communication scenario. In addition, we devised a novel user-centered deep reinforcement learning approach to find a near-optimal solution. Extensive experiments demonstrate that our approach can lead to remarkable results under various requirements and constraints.

cs.NI↗
arXiv2023

Logic Traps in Evaluating Attribution Scores

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features on model predictions. As an explanation method, the evaluation criteria of attribution methods is how accurately it re-reflects the actual reasoning process of the model (faithfulness). Meanwhile, since the reasoning process of deep models is inaccessible, researchers design various evaluation methods to demonstrate their arguments. However, some crucial logic traps in these evaluation methods are ignored in most works, causing inaccurate evaluation and unfair comparison. This paper systematically reviews existing methods for evaluating attribution scores and summarizes the logic traps in these methods. We further conduct experiments to demonstrate the existence of each logic trap. Through both the theoretical and experimental analysis, we hope to increase attention on the inaccurate evaluation of attribution scores. Moreover, with this paper, we suggest stopping focusing on improving performance under unreliable evaluation systems and starting efforts on reducing the impact of proposed logic traps

cs.LG↗
arXiv2023

Before and after China's new Data Laws: Privacy in Apps

Privacy in apps is a topic of widespread interest because many apps collect and share large amounts of highly sensitive information. In response, China introduced a range of new data protection laws over recent years, notably the Personal Information Protection Law (PIPL) in 2021. So far, there exists limited research on the impacts of these new laws on apps' privacy practices. To address this gap, this paper analyses data collection in pairs of 634 Chinese iOS apps, one version from early 2020 and one from late 2021. Our work finds that many more apps now implement consent. Yet, those end-users that decline consent will often be forced to exit the app. Fewer apps now collect data without consent but many still integrate tracking libraries. We see our findings as characteristic of a first iteration at Chinese data regulation with room for improvement.

cs.CY↗
arXiv2023

Trust Explanations to Do What They Say

How much are we to trust a decision made by an AI algorithm? Trusting an algorithm without cause may lead to abuse, and mistrusting it may similarly lead to disuse. Trust in an AI is only desirable if it is warranted; thus, calibrating trust is critical to ensuring appropriate use. In the name of calibrating trust appropriately, AI developers should provide contracts specifying use cases in which an algorithm can and cannot be trusted. Automated explanation of AI outputs is often touted as a method by which trust can be built in the algorithm. However, automated explanations arise from algorithms themselves, so trust in these explanations is similarly only desirable if it is warranted. Developers of algorithms explaining AI outputs (xAI algorithms) should provide similar contracts, which should specify use cases in which an explanation can and cannot be trusted.

cs.HC↗