arXiv subjects

Wen Zhang

Publications and source records attributed to Wen Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2022

Ruleformer: Context-aware Differentiable Rule Mining over Knowledge Graph

Rule mining is an effective approach for reasoning over knowledge graph (KG). Existing works mainly concentrate on mining rules. However, there might be several rules that could be applied for reasoning for one relation, and how to select appropriate rules for completion of different triples has not been discussed. In this paper, we propose to take the context information into consideration, which helps select suitable rules for the inference tasks. Based on this idea, we propose a transformer-based rule mining approach, Ruleformer. It consists of two blocks: 1) an encoder extracting the context information from subgraph of head entities with modified attention mechanism, and 2) a decoder which aggregates the subgraph information from the encoder output and generates the probability of relations for each step of reasoning. The basic idea behind Ruleformer is regarding rule mining process as a sequence to sequence task. To make the subgraph a sequence input to the encoder and retain the graph structure, we devise a relational attention mechanism in Transformer. The experiment results show the necessity of considering these information in rule mining task and the effectiveness of our model.

cs.LO↗

arXiv2022

Joint-optimization of Node placement and UAV's Trajectory for Self-sustaining Air-Ground IoT system

Due to the sustainable power supply and environment-friendly features, self-powered IoT devices have been increasingly employed in various fields such as providing observation data in remote areas, especially in rural areas or post-disaster scenarios. Generally, through multi-hop relay, the sensed data of those self-powered IoT devices are collected by the sink node which connects to the IoT backbones. However, due to the remoteness, the sink needs to be located at the border of the monitoring area where both the backbone of IoT and electrical infrastructures are accessible. Under such deployment, significant data flow and relay overhead will incur considering the large scale of the monitoring area. Motivated by this issue, this paper aims to design a UAV-assisted self-powered heterogeneous system to provide comprehensive monitoring data. In this system, because of the superiority of the unmanned aerial vehicle (UAV) in the easy deployment, We dispatch UAV collects data from self-powered IoT devices, periodically so as to alleviate the data overflow. Moreover, based on that the self-powered IoT devices are expected to have a more considerable capability in the heavy data flow area, we also developed a placement upgrade strategy to upgrade the general homogeneous self-powered IoT system to the heterogeneous self-powered IoT system. Simulation results indicated the developed UAV-assisted self-powered heterogeneous system can achieve around $1.28\times$ the amount of data delivery to sink compared with the homogeneous self-powered IoT system.

eess.SP↗

arXiv2022

Overpotential decomposition enabled decoupling of complex kinetic processes in battery electrodes

Identifying overpotential components of electrochemical systems enables quantitative analysis of polarization contributions of kinetic processes under practical operating conditions. However, the inherently coupled kinetic processes lead to an enormous challenge in measuring individual overpotentials, particularly in composite electrodes of lithium-ion batteries. Herein, the full decomposition of electrode overpotential is realized by the collaboration of single-layer structured particle electrode (SLPE) constructions and time-resolved potential measurements, explicitly revealing the evolution of kinetic processes. Perfect prediction of the discharging profiles is achieved via potential measurements on SLPEs, even in extreme polarization conditions. By decoupling overpotentials in different electrode/cell structures and material systems, the dominant limiting processes of battery rate performance are uncovered, based on which the optimization of electrochemical kinetics can be conducted. Our study not only shades light on decoupling complex kinetics in electrochemical systems, but also provides vitally significant guidance for the rational design of high-performance batteries.

physics.chem-ph↗

arXiv2022

Disentangled Ontology Embedding for Zero-shot Learning

Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). However, existing ZSL methods that utilize KGs all neglect the intrinsic complexity of inter-class relationships represented in KGs. One typical feature is that a class is often related to other classes in different semantic aspects. In this paper, we focus on ontologies for augmenting ZSL, and propose to learn disentangled ontology embeddings guided by ontology properties to capture and utilize more fine-grained class relationships in different aspects. We also contribute a new ZSL framework named DOZSL, which contains two new ZSL solutions based on generative models and graph propagation models, respectively, for effectively utilizing the disentangled ontology embeddings. Extensive evaluations have been conducted on five benchmarks across zero-shot image classification (ZS-IMGC) and zero-shot KG completion (ZS-KGC). DOZSL often achieves better performance than the state-of-the-art, and its components have been verified by ablation studies and case studies. Our codes and datasets are available at https://github.com/zjukg/DOZSL.

cs.AI↗

arXiv2022

Evidence of Spin Frustration in Vanadium Diselenide Monolayer Magnet

Monolayer VSe2, featuring both charge density wave and magnetism phenomena, represents a unique van der Waals magnet in the family of metallic two-dimensional transition-metal dichalcogenides (2D-TMDs). Herein, by means of in-situ microscopic and spectroscopic techniques, including scanning tunneling microscopy/spectroscopy, synchrotron X-ray and angle-resolved photoemission, and X-ray absorption, direct spectroscopic signatures are established, that identify the metallic 1T-phase and vanadium 3d1 electronic configuration in monolayer VSe2 grown on graphite by molecular-beam epitaxy. Element-specific X-ray magnetic circular dichroism, complemented with magnetic susceptibility measurements, further reveals monolayer VSe2 as a frustrated magnet, with its spins exhibiting subtle correlations, albeit in the absence of a long-range magnetic order down to 2 K and up to a 7 T magnetic field. This observation is attributed to the relative stability of the ferromagnetic and antiferromagnetic ground states, arising from its atomic-scale structural features, such as rotational disorders and edges. The results of this study extend the current understanding of metallic 2D-TMDs in the search for exotic low-dimensional quantum phenomena, and stimulate further theoretical and experimental studies on van der Waals monolayer magnets.

cond-mat.mtrl-sci↗

arXiv2022

Magnetic Transition in Monolayer VSe2 via Interface Hybridization

Magnetism in monolayer (ML) VSe2 has attracted broad interest in spintronics while existing reports have not reached consensus. Using element-specific X-ray magnetic circular dichroism, a magnetic transition in ML VSe2 has been demonstrated at the contamination-free interface between Co and VSe2. Via interfacial hybridization with Co atomic overlayer, a magnetic moment of about 0.4 uB per V atom in ML VSe2 is revealed, approaching values predicted by previous theoretical calculations. Promotion of the ferromagnetism in ML VSe2 is accompanied by its antiferromagnetic coupling to Co and a reduction in the spin moment of Co. In comparison to the absence of this interface-induced ferromagnetism at the Fe/MLMoSe2 interface, these findings at the Co/ML-VSe2 interface provide clear proof that the ML VSe2, initially with magnetic disorder, is on the verge of magnetic transition.

cond-mat.mtrl-sci↗

arXiv2022

Blockaid: Data Access Policy Enforcement for Web Applications

Modern web applications serve large amounts of sensitive user data, access to which is typically governed by data-access policies. Enforcing such policies is crucial to preventing improper data access, and prior work has proposed many enforcement mechanisms. However, these prior methods either alter application semantics or require adopting a new programming model; the former can result in unexpected application behavior, while the latter cannot be used with existing web frameworks. Blockaid is an access-policy enforcement system that preserves application semantics and is compatible with existing web frameworks. It intercepts database queries from the application, attempts to verify that each query is policy-compliant, and blocks queries that are not. It verifies policy compliance using SMT solvers and generalizes and caches previous compliance decisions for better performance. We show that Blockaid supports existing web applications while requiring minimal code changes and adding only modest overheads.

cs.DB↗

arXiv2022

Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting

We study the knowledge extrapolation problem to embed new components (i.e., entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing KG needs to embed an emerging KG with unseen entities and relations. To solve this problem, we introduce the meta-learning setting, where a set of tasks are sampled on the existing KG to mimic the link prediction task on the emerging KG. Based on sampled tasks, we meta-train a graph neural network framework that can construct features for unseen components based on structural information and output embeddings for them. Experimental results show that our proposed method can effectively embed unseen components and outperforms models that consider inductive settings for KGs and baselines that directly use conventional KG embedding methods.

cs.CL↗

arXiv2022

Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding

Knowledge graphs (KGs) consisting of a large number of triples have become widespread recently, and many knowledge graph embedding (KGE) methods are proposed to embed entities and relations of a KG into continuous vector spaces. Such embedding methods simplify the operations of conducting various in-KG tasks (e.g., link prediction) and out-of-KG tasks (e.g., question answering). They can be viewed as general solutions for representing KGs. However, existing KGE methods are not applicable to inductive settings, where a model trained on source KGs will be tested on target KGs with entities unseen during model training. Existing works focusing on KGs in inductive settings can only solve the inductive relation prediction task. They can not handle other out-of-KG tasks as general as KGE methods since they don't produce embeddings for entities. In this paper, to achieve inductive knowledge graph embedding, we propose a model MorsE, which does not learn embeddings for entities but learns transferable meta-knowledge that can be used to produce entity embeddings. Such meta-knowledge is modeled by entity-independent modules and learned by meta-learning. Experimental results show that our model significantly outperforms corresponding baselines for in-KG and out-of-KG tasks in inductive settings.

cs.LG↗

arXiv2022

In-plane anisotropic response to the uniaxial pressure in the hidden order state of URu$_2$Si$_2$

We studied the uniaxial-pressure dependence of the resistivity for URu$_{2-x}$Fe$_x$Si$_2$ samples with $x$ = 0 and 0.2, which host a hidden order (HO) and a large-moment antiferromagnetic (LMAFM) phase, respectively. For both samples, the elastoresistivity $ζ$ shows a seemingly divergent behavior above the transition temperature $T_0$ and a quick decrease below it. We found that the temperature dependence of $ζ$ for both samples can be well described by assuming the uniaxial pressure effect on the gap or certain energy scale except for $ζ_{(110)}$ of the $x$ = 0 sample, which exhibits a non-zero residual value at 0 K. We show that this provides a qualitative difference between the HO and LMAFM phases. Our results suggest that there is an in-plane anisotropic response to the uniaxial pressure that only exists in the hidden order state without necessarily breaking the rotational lattice symmetry.

cond-mat.str-el↗

arXiv2022

A Deep Learning Galerkin Method for the Closed-Loop Geothermal System

There has been an arising trend of adopting deep learning methods to study partial differential equations (PDEs). This article is to propose a Deep Learning Galerkin Method (DGM) for the closed-loop geothermal system, which is a new coupled multi-physics PDEs and mainly consists of a framework of underground heat exchange pipelines to extract the geothermal heat from the geothermal reservoir. This method is a natural combination of Galerkin Method and machine learning with the solution approximated by a neural network instead of a linear combination of basis functions. We train the neural network by randomly sampling the spatiotemporal points and minimize loss function to satisfy the differential operators, initial condition, boundary and interface conditions. Moreover, the approximate ability of the neural network is proved by the convergence of the loss function and the convergence of the neural network to the exact solution in L^2 norm under certain conditions. Finally, some numerical examples are carried out to demonstrate the approximation ability of the neural networks intuitively.

math.NA↗

arXiv2022

Hierarchical Graph Representation Learning for the Prediction of Drug-Target Binding Affinity

The identification of drug-target binding affinity (DTA) has attracted increasing attention in the drug discovery process due to the more specific interpretation than binary interaction prediction. Recently, numerous deep learning-based computational methods have been proposed to predict the binding affinities between drugs and targets benefiting from their satisfactory performance. However, the previous works mainly focus on encoding biological features and chemical structures of drugs and targets, with a lack of exploiting the essential topological information from the drug-target affinity network. In this paper, we propose a novel hierarchical graph representation learning model for the drug-target binding affinity prediction, namely HGRL-DTA. The main contribution of our model is to establish a hierarchical graph learning architecture to incorporate the intrinsic properties of drug/target molecules and the topological affinities of drug-target pairs. In this architecture, we adopt a message broadcasting mechanism to integrate the hierarchical representations learned from the global-level affinity graph and the local-level molecular graph. Besides, we design a similarity-based embedding map to solve the cold start problem of inferring representations for unseen drugs and targets. Comprehensive experimental results under different scenarios indicate that HGRL-DTA significantly outperforms the state-of-the-art models and shows better model generalization among all the scenarios.

cs.LG↗

arXiv2022

Molecular Contrastive Learning with Chemical Element Knowledge Graph

Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes self-supervision signals and has no requirements for human annotations. However, prior works fail to incorporate fundamental domain knowledge into graph semantics and thus ignore the correlations between atoms that have common attributes but are not directly connected by bonds. To address these issues, we construct a Chemical Element Knowledge Graph (KG) to summarize microscopic associations between elements and propose a novel Knowledge-enhanced Contrastive Learning (KCL) framework for molecular representation learning. KCL framework consists of three modules. The first module, knowledge-guided graph augmentation, augments the original molecular graph based on the Chemical Element KG. The second module, knowledge-aware graph representation, extracts molecular representations with a common graph encoder for the original molecular graph and a Knowledge-aware Message Passing Neural Network (KMPNN) to encode complex information in the augmented molecular graph. The final module is a contrastive objective, where we maximize agreement between these two views of molecular graphs. Extensive experiments demonstrated that KCL obtained superior performances against state-of-the-art baselines on eight molecular datasets. Visualization experiments properly interpret what KCL has learned from atoms and attributes in the augmented molecular graphs. Our codes and data are available at https://github.com/ZJU-Fangyin/KCL.

cs.LG↗

arXiv2022

PKGM: A Pre-trained Knowledge Graph Model for E-commerce Application

In recent years, knowledge graphs have been widely applied as a uniform way to organize data and have enhanced many tasks requiring knowledge. In online shopping platform Taobao, we built a billion-scale e-commerce product knowledge graph. It organizes data uniformly and provides item knowledge services for various tasks such as item recommendation. Usually, such knowledge services are provided through triple data, while this implementation includes (1) tedious data selection works on product knowledge graph and (2) task model designing works to infuse those triples knowledge. More importantly, product knowledge graph is far from complete, resulting error propagation to knowledge enhanced tasks. To avoid these problems, we propose a Pre-trained Knowledge Graph Model (PKGM) for the billion-scale product knowledge graph. On the one hand, it could provide item knowledge services in a uniform way with service vectors for embedding-based and item-knowledge-related task models without accessing triple data. On the other hand, it's service is provided based on implicitly completed product knowledge graph, overcoming the common the incomplete issue. We also propose two general ways to integrate the service vectors from PKGM into downstream task models. We test PKGM in five knowledge-related tasks, item classification, item resolution, item recommendation, scene detection and sequential recommendation. Experimental results show that PKGM introduces significant performance gains on these tasks, illustrating the useful of service vectors from PKGM.

cs.AI↗

arXiv2022

NeuralKG: An Open Source Library for Diverse Representation Learning of Knowledge Graphs

NeuralKG is an open-source Python-based library for diverse representation learning of knowledge graphs. It implements three different series of Knowledge Graph Embedding (KGE) methods, including conventional KGEs, GNN-based KGEs, and Rule-based KGEs. With a unified framework, NeuralKG successfully reproduces link prediction results of these methods on benchmarks, freeing users from the laborious task of reimplementing them, especially for some methods originally written in non-python programming languages. Besides, NeuralKG is highly configurable and extensible. It provides various decoupled modules that can be mixed and adapted to each other. Thus with NeuralKG, developers and researchers can quickly implement their own designed models and obtain the optimal training methods to achieve the best performance efficiently. We built an website in http://neuralkg.zjukg.cn to organize an open and shared KG representation learning community. The source code is all publicly released at https://github.com/zjukg/NeuralKG.

cs.LG↗

arXiv2022

Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective

Knowledge graph (KG) reasoning is becoming increasingly popular in both academia and industry. Conventional KG reasoning based on symbolic logic is deterministic, with reasoning results being explainable, while modern embedding-based reasoning can deal with uncertainty and predict plausible knowledge, often with high efficiency via vector computation. A promising direction is to integrate both logic-based and embedding-based methods, with the vision to have advantages of both. It has attracted wide research attention with more and more works published in recent years. In this paper, we comprehensively survey these works, focusing on how logics and embeddings are integrated. We first briefly introduce preliminaries, then systematically categorize and discuss works of logic and embedding-aware KG reasoning from different perspectives, and finally conclude and discuss the challenges and further directions.

cs.AI↗

arXiv2022

Energy Harvesting Aware Multi-hop Routing Policy in Distributed IoT System Based on Multi-agent Reinforcement Learning

Energy harvesting technologies offer a promising solution to sustainably power an ever-growing number of Internet of Things (IoT) devices. However, due to the weak and transient natures of energy harvesting, IoT devices have to work intermittently rendering conventional routing policies and energy allocation strategies impractical. To this end, this paper, for the very first time, developed a distributed multi-agent reinforcement algorithm known as global actor-critic policy (GAP) to address the problem of routing policy and energy allocation together for the energy harvesting powered IoT system. At the training stage, each IoT device is treated as an agent and one universal model is trained for all agents to save computing resources. At the inference stage, packet delivery rate can be maximized. The experimental results show that the proposed GAP algorithm achieves around 1.28 times and 1.24 times data transmission rate than that of the Q-table and ESDSRAA algorithm, respectively.

cs.NI↗

arXiv2022

CDNNs: The coupled deep neural networks for coupling of the Stokes and Darcy-Forchheimer problems

In this article, we present an efficient deep learning method called coupled deep neural networks (CDNNs) for coupled physical problems. Our method compiles the interface conditions of the coupled PDEs into the networks properly and can be served as an efficient alternative to the complex coupled problems. To impose energy conservation constraints, the CDNNs utilize simple fully connected layers and a custom loss function to perform the model training process as well as the physical property of the exact solution. The approach can be beneficial for the following reasons: Firstly, we sampled randomly and only input spatial coordinates without being restricted by the nature of samples. Secondly, our method is meshfree which makes it more efficient than the traditional methods. Finally, our method is parallel and can solve multiple variables independently at the same time. We give the theory to guarantee the convergence of the loss function and the convergence of the neural networks to the exact solution. Some numerical experiments are performed and discussed to demonstrate the performance of the proposed method.

math.NA↗