arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 469 records · Page 26Linked to original sources

arXiv2022

Zero Trust Architecture for 6G Security

The upcoming sixth generation (6G) network is envisioned to be more open and heterogeneous than earlier generations. This challenges conventional security architectures, which typically rely on the construction of a security perimeter at network boundaries. In this article, we propose a software-defined zero trust architecture (ZTA) for 6G networks, which is promising for establishing an elastic and scalable security regime. This architecture achieves secure access control through adaptive collaborations among the involved control domains, and can effectively prevent malicious access behaviors such as distributed denial of service (DDoS) attacks, malware spread, and zero-day exploits. We also introduce key design aspects of this architecture and show the simulation results of a case study, which shows the effectiveness and robustness of ZTA for 6G. Furthermore, we discuss open issues to further promote this new architecture.

cs.NI↗

arXiv2022

Inferring Network Structure with Unobservable Nodes from Time Series Data

Network structures play important roles in social, technological and biological systems. However, the observable nodes and connections in real cases are often incomplete or unavailable due to measurement errors, private protection issues, or other problems. Therefore, inferring the complete network structure is useful for understanding human interactions and complex dynamics. The existing studies have not fully solved the problem of inferring network structure with partial information about connections or nodes. In this paper, we tackle the problem by utilizing time-series data generated by network dynamics. We regard the network inference problem based on dynamical time series data as a problem of minimizing errors for predicting states of observable nodes and proposed a novel data-driven deep learning model called Gumbel-softmax Inference for Network (GIN) to solve the problem under incomplete information. The GIN framework includes three modules: a dynamics learner, a network generator, and an initial state generator to infer the unobservable parts of the network. We implement experiments on artificial and empirical social networks with discrete and continuous dynamics. The experiments show that our method can infer the unknown parts of the structure and the initial states of the observable nodes with up to 90\% accuracy. The accuracy declines linearly with the increase of the fractions of unobservable nodes. Our framework may have wide applications where the network structure is hard to obtain and the time series data is rich.

cs.SI↗

arXiv2022

NEDMP: Neural Enhanced Dynamic Message Passing

Predicting stochastic spreading processes on complex networks is critical in epidemic control, opinion propagation, and viral marketing. We focus on the problem of inferring the time-dependent marginal probabilities of states for each node which collectively quantifies the spreading results. Dynamic Message Passing (DMP) has been developed as an efficient inference algorithm for several spreading models, and it is asymptotically exact on locally tree-like networks. However, DMP can struggle in diffusion networks with lots of local loops. We address this limitation by using Graph Neural Networks (GNN) to learn the dependency amongst messages implicitly. Specifically, we propose a hybrid model in which the GNN module runs jointly with DMP equations. The GNN module refines the aggregated messages in DMP iterations by learning from simulation data. We demonstrate numerically that after training, our model's inference accuracy substantially outperforms DMP in conditions of various network structure and dynamics parameters. Moreover, compared to pure data-driven models, the proposed hybrid model has a better generalization ability for out-of-training cases, profiting from the explicitly utilized dynamics priors in the hybrid model. A PyTorch implementation of our model is at https://github.com/FeiGSSS/NEDMP.

cs.SI↗

arXiv2022

Deep Graph Learning for Spatially-Varying Indoor Lighting Prediction

Lighting prediction from a single image is becoming increasingly important in many vision and augmented reality (AR) applications in which shading and shadow consistency between virtual and real objects should be guaranteed. However, this is a notoriously ill-posed problem, especially for indoor scenarios, because of the complexity of indoor luminaires and the limited information involved in 2D images. In this paper, we propose a graph learning-based framework for indoor lighting estimation. At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view. Our lighting model builds 128 evenly distributed SGs over the indoor panorama, where each SG encoding the lighting and the depth around that node. The proposed GCN then learns the mapping from the input image to DSGLight. Compared with existing lighting models, our DSGLight encodes both direct lighting and indirect environmental lighting more faithfully and compactly. It also makes network training and inference more stable. The estimated depth distribution enables temporally stable shading and shadows under spatially-varying lighting. Through thorough experiments, we show that our method obviously outperforms existing methods both qualitatively and quantitatively.

cs.CV↗

arXiv2022

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

Most set prediction models in deep learning use set-equivariant operations, but they actually operate on multisets. We show that set-equivariant functions cannot represent certain functions on multisets, so we introduce the more appropriate notion of multiset-equivariance. We identify that the existing Deep Set Prediction Network (DSPN) can be multiset-equivariant without being hindered by set-equivariance and improve it with approximate implicit differentiation, allowing for better optimization while being faster and saving memory. In a range of toy experiments, we show that the perspective of multiset-equivariance is beneficial and that our changes to DSPN achieve better results in most cases. On CLEVR object property prediction, we substantially improve over the state-of-the-art Slot Attention from 8% to 77% in one of the strictest evaluation metrics because of the benefits made possible by implicit differentiation.

cs.LG↗

arXiv2022

Learning Robust Representation through Graph Adversarial Contrastive Learning

Existing studies show that node representations generated by graph neural networks (GNNs) are vulnerable to adversarial attacks, such as unnoticeable perturbations of adjacent matrix and node features. Thus, it is requisite to learn robust representations in graph neural networks. To improve the robustness of graph representation learning, we propose a novel Graph Adversarial Contrastive Learning framework (GraphACL) by introducing adversarial augmentations into graph self-supervised learning. In this framework, we maximize the mutual information between local and global representations of a perturbed graph and its adversarial augmentations, where the adversarial graphs can be generated in either supervised or unsupervised approaches. Based on the Information Bottleneck Principle, we theoretically prove that our method could obtain a much tighter bound, thus improving the robustness of graph representation learning. Empirically, we evaluate several methods on a range of node classification benchmarks and the results demonstrate GraphACL could achieve comparable accuracy over previous supervised methods.

cs.LG↗

arXiv2022

Wireless Energy Transfer in RIS-Aided Cell-Free Massive MIMO Systems: Opportunities and Challenges

In future sixth-generation (6G) mobile networks, the Internet-of-Everything (IoE) is expected to provide extremely massive connectivity for small battery-powered devices. Indeed, massive devices with limited energy storage capacity impose persistent energy demand hindering the lifetime of communication networks. As a remedy, wireless energy transfer (WET) is a key technology to address these critical energy supply issues. On the other hand, cell-free (CF) massive multiple-input multiple-output (MIMO) systems offer an efficient network architecture to realize the roll-out of the IoE. In this article, we first propose the paradigm of reconfigurable intelligent surface (RIS)-aided CF massive MIMO systems for WET, including its potential application scenarios and system architecture. The four-stage transmission procedure is discussed and analyzed to illustrate the practicality of the architecture. Then we put forward and analyze the hardware design of RIS. Particularly, we discuss the three corresponding operating modes and the amalgamation of WET technology and RIS-aided CF massive MIMO. Representative simulation results are given to confirm the superior performance achieved by our proposed schemes. Also, we investigate the optimal location of deploying multiple RISs to achieve the best system performance. Finally, several important research directions of RIS-aided CF massive MIMO systems with WET are presented to inspire further potential investigation.

cs.IT↗

arXiv2022

Reconfigurable Intelligent Surfaces with Outdated Channel State Information: Centralized vs. Distributed Deployments

In this paper, we investigate the performance of an RIS-aided wireless communication system subject to outdated channel state information that may operate in both the near- and far-field regions. In particular, we take two RIS deployment strategies into consideration: (i) the centralized deployment, where all the reflecting elements are installed on a single RIS and (ii) the distributed deployment, where the same number of reflecting elements are placed on multiple RISs. For both deployment strategies, we derive accurate closed-form approximations for the ergodic capacity, and we introduce tight upper and lower bounds for the ergodic capacity to obtain useful design insights. From this analysis, we unveil that an increase of the transmit power, the Rician-K factor, the accuracy of the channel state information and the number of reflecting elements help improve the system performance. Moreover, we prove that the centralized RIS-aided deployment may achieve a higher ergodic capacity as compared with the distributed RIS-aided deployment when the RIS is located near the base station or near the user. In different setups, on the other hand, we prove that the distributed deployment outperforms the centralized deployment. Finally, the analytical results are verified by using Monte Carlo simulations.

cs.IT↗

arXiv2022

PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an unfixed number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.

cs.CV↗

arXiv2022

Semi-Supervised Co-Analysis of 3D Shape Styles from Projected Lines

We present a semi-supervised co-analysis method for learning 3D shape styles from projected feature lines, achieving style patch localization with only weak supervision. Given a collection of 3D shapes spanning multiple object categories and styles, we perform style co-analysis over projected feature lines of each 3D shape and then backproject the learned style features onto the 3D shapes. Our core analysis pipeline starts with mid-level patch sampling and pre-selection of candidate style patches. Projective features are then encoded via patch convolution. Multi-view feature integration and style clustering are carried out under the framework of partially shared latent factor (PSLF) learning, a multi-view feature learning scheme. PSLF achieves effective multi-view feature fusion by distilling and exploiting consistent and complementary feature information from multiple views, while also selecting style patches from the candidates. Our style analysis approach supports both unsupervised and semi-supervised analysis. For the latter, our method accepts both user-specified shape labels and style-ranked triplets as clustering constraints.We demonstrate results from 3D shape style analysis and patch localization as well as improvements over state-of-the-art methods. We also present several applications enabled by our style analysis.

cs.GR↗

arXiv2022

Learning Multi-granularity User Intent Unit for Session-based Recommendation

Session-based recommendation aims to predict a user's next action based on previous actions in the current session. The major challenge is to capture authentic and complete user preferences in the entire session. Recent work utilizes graph structure to represent the entire session and adopts Graph Neural Network to encode session information. This modeling choice has been proved to be effective and achieved remarkable results. However, most of the existing studies only consider each item within the session independently and do not capture session semantics from a high-level perspective. Such limitation often leads to severe information loss and increases the difficulty of capturing long-range dependencies within a session. Intuitively, compared with individual items, a session snippet, i.e., a group of locally consecutive items, is able to provide supplemental user intents which are hardly captured by existing methods. In this work, we propose to learn multi-granularity consecutive user intent unit to improve the recommendation performance. Specifically, we creatively propose Multi-granularity Intent Heterogeneous Session Graph which captures the interactions between different granularity intent units and relieves the burden of long-dependency. Moreover, we propose the Intent Fusion Ranking module to compose the recommendation results from various granularity user intents. Compared with current methods that only leverage intents from individual items, IFR benefits from different granularity user intents to generate more accurate and comprehensive session representation, thus eventually boosting recommendation performance. We conduct extensive experiments on five session-based recommendation datasets and the results demonstrate the effectiveness of our method.

cs.IR↗

arXiv2021

Learning and Generalizing Variable Impedance Manipulation Skills from Human Demonstrations

By learning Variable Impedance Control policy, robot assistants can intelligently adapt their manipulation compliance to ensure both safe interaction and proper task completion when operating in human-robot interaction environments. In this paper, we propose a DMP-based framework that learns and generalizes variable impedance manipulation skills from human demonstrations. This framework improves robots$'$ adaptability to environment changes(i.e. the weight and shape changes of grasping object at the robot end-effector) and inherits the efficiency of demonstration-variance-based stiffness estimation methods. Besides, with our stiffness estimation method, we generate not only translational stiffness profiles but also rotational stiffness profiles that are ignored or incomplete in most learning Variable Impedance Control papers. Real-world experiments on a 7 DoF redundant robot manipulator have been conducted to validate the effectiveness of our framework.

cs.RO↗

arXiv2021

Phase-modulated Autler-Townes splitting in a giant-atom system within waveguide QED

The nonlocal emitter-waveguide coupling, which gives birth to the so called giant atom, represents a new paradigm in the field of quantum optics and waveguide QED. In this paper, we investigate the single-photon scattering in a one-dimensional waveguide on a two-level or three-level giant atom. Thanks to the natural interference induced by the back and forth photon transmitted/reflected between the atom-waveguide coupling points, the photon transmission can be dynamically controlled by the periodic phase modulation via adjusting the size of the giant atom. For the two-level giant-atom setup, we demonstrate the energy shift which is dependent on the atomic size. For the driven three-level giant-atom setup, it is of great interest that, the Autler-Townes splitting is dramatically modulated by the giant atom, in which the width of the transmission valleys (reflection range) is tunable in terms of the atomic size. Our investigation will be beneficial to the photon or phonon control in quantum network based on mesoscopical or even macroscopical quantum nodes involving the giant atom.

quant-ph↗

arXiv2021

EndHiC: assemble large contigs into chromosomal-level scaffolds using the Hi-C links from contig ends

Motivation: The application of PacBio HiFi and ultra-long ONT reads have achieved huge progress in the contig-level assembly, but it is still challenging to assemble large contigs into chromosomes with available Hi-C scaffolding software, which all compute the contact value between contigs using the Hi-C links from the whole contig regions. As the Hi-C links of two adjacent contigs concentrate only at the neighbor ends of the contigs, larger contig size will reduce the power to differentiate adjacent (signal) and non-adjacent (noise) contig linkages, leading to a higher rate of mis-assembly. Results: We present a software package EndHiC, which is suitable to assemble large contigs (> 1-Mb) into chromosomal-level scaffolds, using Hi-C links from only the contig end regions instead of the whole contig regions. Benefiting from the increased signal to noise ratio, EndHiC achieves much higher scaffolding accuracy compared to existing software LACHESIS, ALLHiC, and 3D-DNA. Moreover, EndHiC has few parameters, runs 10-1000 times faster than existing software, needs trivial memory, provides robustness evaluation, and allows graphic viewing of the scaffold results. The high scaffolding accuracy and user-friendly interface of EndHiC, liberate the users from labor-intensive manual checks and revision works. Availability and implementation: EndHiC is written in Perl, and is freely available at https://github.com/fanagislab/EndHiC. Contact: fanwei@caas.cn and milrazhang@163.com Supplementary information: Supplementary data are available at Bioinformatics online.

q-bio.GN↗

arXiv2021

Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning

Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yielded significant improvements on this task. The sequence representation plays a key role in the learning of matching degree between the dialogue context and the response. However, we observe that different context-response pairs sharing the same context always have a greater similarity in the sequence representations calculated by PLMs, which makes it hard to distinguish positive responses from negative ones. Motivated by this, we propose a novel \textbf{F}ine-\textbf{G}rained \textbf{C}ontrastive (FGC) learning method for the response selection task based on PLMs. This FGC learning strategy helps PLMs to generate more distinguishable matching representations of each dialogue at fine grains, and further make better predictions on choosing positive responses. Empirical studies on two benchmark datasets demonstrate that the proposed FGC learning method can generally and significantly improve the model performance of existing PLM-based matching models.

cs.CL↗

arXiv2021

RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation

Real-time location inference of social media users is the fundamental of some spatial applications such as localized search and event detection. While tweet text is the most commonly used feature in location estimation, most of the prior works suffer from either the noise or the sparsity of textual features. In this paper, we aim to tackle these two problems. We use topic modeling as a building block to characterize the geographic topic variation and lexical variation so that "one-hot" encoding vectors will no longer be directly used. We also incorporate other features which can be extracted through the Twitter streaming API to overcome the noise problem. Experimental results show that our RATE algorithm outperforms several benchmark methods, both in the precision of region classification and the mean distance error of latitude and longitude regression.

cs.CL↗

arXiv2021

4D Human Body Capture from Egocentric Video via 3D Scene Grounding

We introduce a novel task of reconstructing a time series of second-person 3D human body meshes from monocular egocentric videos. The unique viewpoint and rapid embodied camera motion of egocentric videos raise additional technical barriers for human body capture. To address those challenges, we propose a simple yet effective optimization-based approach that leverages 2D observations of the entire video sequence and human-scene interaction constraint to estimate second-person human poses, shapes, and global motion that are grounded on the 3D environment captured from the egocentric view. We conduct detailed ablation studies to validate our design choice. Moreover, we compare our method with the previous state-of-the-art method on human motion capture from monocular video, and show that our method estimates more accurate human-body poses and shapes under the challenging egocentric setting. In addition, we demonstrate that our approach produces more realistic human-scene interaction.

cs.CV↗

arXiv2021

Revisiting Self-Training for Few-Shot Learning of Language Model

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM. Given two views of a text sample via weak and strong augmentation techniques, SFLM generates a pseudo label on the weakly augmented version. Then, the model predicts the same pseudo label when fine-tuned with the strongly augmented version. This simple approach is shown to outperform other state-of-the-art supervised and semi-supervised counterparts on six sentence classification and six sentence-pair classification benchmarking tasks. In addition, SFLM only relies on a few in-domain unlabeled data. We conduct a comprehensive analysis to demonstrate the robustness of our proposed approach under various settings, including augmentation techniques, model scale, and few-shot knowledge transfer across tasks.

cs.CL↗