arXiv subjects

Jiang Zhang

Publications and source records attributed to Jiang Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2021

HARPO: Learning to Subvert Online Behavioral Advertising

Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat. Unfortunately, existing privacy-enhancing tools are not always effective against online advertising and tracking. We propose Harpo, a principled learning-based approach to subvert online behavioral advertising through obfuscation. Harpo uses reinforcement learning to adaptively interleave real page visits with fake pages to distort a tracker's view of a user's browsing profile. We evaluate Harpo against real-world user profiling and ad targeting models used for online behavioral advertising. The results show that Harpo improves privacy by triggering more than 40% incorrect interest segments and 6x higher bid values. Harpo outperforms existing obfuscation tools by as much as 16x for the same overhead. Harpo is also able to achieve better stealthiness to adversarial detection than existing obfuscation tools. Harpo meaningfully advances the state-of-the-art in leveraging obfuscation to subvert online behavioral advertising

cs.LG↗

arXiv2021

PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting

When predicting PM2.5 concentrations, it is necessary to consider complex information sources since the concentrations are influenced by various factors within a long period. In this paper, we identify a set of critical domain knowledge for PM2.5 forecasting and develop a novel graph based model, PM2.5-GNN, being capable of capturing long-term dependencies. On a real-world dataset, we validate the effectiveness of the proposed model and examine its abilities of capturing both fine-grained and long-term influences in PM2.5 process. The proposed PM2.5-GNN has also been deployed online to provide free forecasting service.

eess.SP↗

arXiv2021

TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data

Tabular data are ubiquitous for the widespread applications of tables and hence have attracted the attention of researchers to extract underlying information. One of the critical problems in mining tabular data is how to understand their inherent semantic structures automatically. Existing studies typically adopt Convolutional Neural Network (CNN) to model the spatial information of tabular structures yet ignore more diverse relational information between cells, such as the hierarchical and paratactic relationships. To simultaneously extract spatial and relational information from tables, we propose a novel neural network architecture, TabularNet. The spatial encoder of TabularNet utilizes the row/column-level Pooling and the Bidirectional Gated Recurrent Unit (Bi-GRU) to capture statistical information and local positional correlation, respectively. For relational information, we design a new graph construction method based on the WordNet tree and adopt a Graph Convolutional Network (GCN) based encoder that focuses on the hierarchical and paratactic relationships between cells. Our neural network architecture can be a unified neural backbone for different understanding tasks and utilized in a multitask scenario. We conduct extensive experiments on three classification tasks with two real-world spreadsheet data sets, and the results demonstrate the effectiveness of our proposed TabularNet over state-of-the-art baselines.

cs.LG↗

arXiv2020

Understanding the mesoscopic scaling patterns within cities

Understanding quantitative relationships between urban elements is crucial for a wide range of applications. The observation at the macroscopic level demonstrates that the aggregated urban quantities (e.g., gross domestic product) scale systematically with population sizes across cities, also known as urban scaling laws. However, at the mesoscopic level, we lack an understanding of whether the simple scaling relationship holds within cities, which is a fundamental question regarding the spatial origin of scaling in urban systems. Here, by analyzing four extensive datasets covering millions of mobile phone users and urban facilities, we investigate the scaling phenomena within cities. We find that the mesoscopic infrastructure volume and socioeconomic activity scale sub- and super-linearly with the active population, respectively. For a same scaling phenomenon, however, the exponents vary in cities of similar population sizes. To explain these empirical observations, we propose a conceptual framework by considering the heterogeneous distributions of population and facilities, and the spatial interactions between them. Analytical and numerical results suggest that, despite the large number of complexities that influence urban activities, the simple interaction rules can effectively explain the observed regularity and heterogeneity in scaling behaviors within cities.

physics.soc-ph↗

arXiv2020

Fairness-guided SMT-based Rectification of Decision Trees and Random Forests

Data-driven decision making is gaining prominence with the popularity of various machine learning models. Unfortunately, real-life data used in machine learning training may capture human biases, and as a result the learned models may lead to unfair decision making. In this paper, we provide a solution to this problem for decision trees and random forests. Our approach converts any decision tree or random forest into a fair one with respect to a specific data set, fairness criteria, and sensitive attributes. The \emph{FairRepair} tool, built based on our approach, is inspired by automated program repair techniques for traditional programs. It uses an SMT solver to decide which paths in the decision tree could have their outcomes flipped to improve the fairness of the model. Our experiments on the well-known adult dataset from UC Irvine demonstrate that FairRepair scales to realistic decision trees and random forests. Furthermore, FairRepair provides formal guarantees about soundness and completeness of finding a repair. Since our fairness-guided repair technique repairs decision trees and random forests obtained from a given (unfair) data-set, it can help to identify and rectify biases in decision-making in an organisation.

cs.LG↗

arXiv2020

An interpretable planning bot for pancreas stereotactic body radiation therapy

Pancreas stereotactic body radiotherapy treatment planning requires planners to make sequential, time consuming interactions with the treatment planning system (TPS) to reach the optimal dose distribution. We seek to develop a reinforcement learning (RL)-based planning bot to systematically address complex tradeoffs and achieve high plan quality consistently and efficiently. The focus of pancreas SBRT planning is finding a balance between organs-at-risk sparing and planning target volume (PTV) coverage. Planners evaluate dose distributions and make planning adjustments to optimize PTV coverage while adhering to OAR dose constraints. We have formulated such interactions between the planner and the TPS into a finite-horizon RL model. First, planning status features are evaluated based on human planner experience and defined as planning states. Second, planning actions are defined to represent steps that planners would commonly implement to address different planning needs. Finally, we have derived a reward system based on an objective function guided by physician-assigned constraints. The planning bot trained itself with 48 plans augmented from 16 previously treated patients and generated plans for 24 cases in a separate validation set. All 24 bot-generated plans achieve similar PTV coverages compared to clinical plans while satisfying all clinical planning constraints. Moreover, the knowledge learned by the bot can be visualized and interpreted as consistent with human planning knowledge, and the knowledge maps learned in separate training sessions are consistent, indicating reproducibility of the learning process.

physics.med-ph↗

arXiv2020

Gumbel-softmax-based Optimization: A Simple General Framework for Optimization Problems on Graphs

In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints. However, these problems are notorious for their hardness to solve because most of them are NP-hard or NP-complete. Although traditional general methods such as simulated annealing (SA), genetic algorithms (GA) and so forth have been devised to these hard problems, their accuracy and time consumption are not satisfying in practice. In this work, we proposed a simple, fast, and general algorithm framework based on advanced automatic differentiation technique empowered by deep learning frameworks. By introducing Gumbel-softmax technique, we can optimize the objective function directly by gradient descent algorithm regardless of the discrete nature of variables. We also introduce evolution strategy to parallel version of our algorithm. We test our algorithm on three representative optimization problems on graph including modularity optimization from network science, Sherrington-Kirkpatrick (SK) model from statistical physics, maximum independent set (MIS) and minimum vertex cover (MVC) problem from combinatorial optimization on graph. High-quality solutions can be obtained with much less time consuming compared to traditional approaches.

cs.LG↗

arXiv2020

Inference for Network Structure and Dynamics from Time Series Data via Graph Neural Network

Network structures in various backgrounds play important roles in social, technological, and biological systems. However, the observable network structures in real cases are often incomplete or unavailable due to measurement errors or private protection issues. Therefore, inferring the complete network structure is useful for understanding complex systems. The existing studies have not fully solved the problem of inferring network structure with partial or no 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 future states and proposed a novel data-driven deep learning model called Gumbel Graph Network (GGN) to solve the two kinds of network inference problems: Network Reconstruction and Network Completion. For the network reconstruction problem, the GGN framework includes two modules: the dynamics learner and the network generator. For the network completion problem, GGN adds a new module called the States Learner to infer missing parts of the network. We carried out experiments on discrete and continuous time series data. The experiments show that our method can reconstruct up to 100% network structure on the network reconstruction task. While the model can also infer the unknown parts of the structure with up to 90% accuracy when some nodes are missing. And the accuracy decays with the increase of the fractions of missing nodes. Our framework may have wide application areas where the network structure is hard to obtained and the time series data is rich.

cs.LG↗

arXiv2019

Link Prediction via Graph Attention Network

Link prediction aims to infer missing links or predicting the future ones based on currently observed partial networks, it is a fundamental problem in network science with tremendous real-world applications. However, conventional link prediction approaches neither have high prediction accuracy nor being capable of revealing the hidden information behind links. To address this problem, we generalize the latest techniques in deep learning on graphs and present a new link prediction model - DeepLinker. Instead of learning node representation with the node label information, DeepLinker uses the links as supervised information. Experiments on five graphs show that DeepLinker can not only achieve the state-of-the-art link prediction accuracy, but also acquire the efficient node representations and node centrality ranking as the byproducts. Although the representations are obtained without any supervised node label information, they still perform well on node ranking and node classification tasks.

cs.SI↗

arXiv2019

Topological Dynamical Decoupling

We show that topological equivalence classes of circles in a two-dimensional square lattice can be used to design dynamical decoupling procedures to protect qubits attached on the edges of the lattice. Based on the circles of the topologically trivial class in the original and the dual lattices, we devise a procedure which removes all kinds of local Hamiltonians from the dynamics of the qubits while keeping information stored in the homological degrees of freedom unchanged. If only the linearly independent interaction and nearest-neighbor two-qubit interactions are concerned, a much simpler procedure which involves the four equivalence classes of circles can be designed. This procedure is compatible with Eulerian and concatenated dynamical decouplings, which make it possible to implement the procedure with bounded-strength controls and for a long time period. As an application, it is shown that our method can be directly generalized to finite square lattices to suppress uncorrectable errors in surface codes.

quant-ph↗

arXiv2019

Gumbel-softmax Optimization: A Simple General Framework for Combinatorial Optimization Problems on Graphs

Many problems in real life can be converted to combinatorial optimization problems (COPs) on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints. However, these problems are notorious for their hardness to solve because most of them are NP-hard or NP-complete. Although traditional general methods such as simulated annealing (SA), genetic algorithms (GA) and so forth have been devised to these hard problems, their accuracy and time consumption are not satisfying in practice. In this work, we proposed a simple, fast, and general algorithm framework called Gumbel-softmax Optimization (GSO) for COPs. By introducing Gumbel-softmax technique which is developed in machine learning community, we can optimize the objective function directly by gradient descent algorithm regardless of the discrete nature of variables. We test our algorithm on four different problems including Sherrington-Kirkpatrick (SK) model, maximum independent set (MIS) problem, modularity optimization, and structural optimization problem. High-quality solutions can be obtained with much less time consuming compared to traditional approaches.

cs.LG↗

arXiv2019

Discovery of room temperature ferromagnetism in metal-free organic semiconductors

Creating magnetic semiconductors that work at warm circumstance is still a great challenge in the physical sciences. Here, we report the discovery of ferromagnetism in the metal-free perylene diimide semiconductor, whose Curie temperature is higher than 400 Kelvin. A solvothermal approach is used to reduce and dissolve the rigid-backbone perylene diimide crystallites, and radical anion aggregates were fabricated by the subsequent self-assembly and oxidation process. Magnetic measurements exhibit the ferromagnetic ordering with the saturated magnetization of 0.48 $μ_{\rm B}$ per molecule and the appreciable magnetic anisotropy. X-ray magnetic circular dichroism spectra suggest the ferromagnetism stems from $π$ orbitals of radicals. Our findings unambitiously demonstrate the long-range ferromagnetic ordering can survive at room temperature in organic semiconductors, although which are intuitively regarded to be nonmagnetic.

cond-mat.mtrl-sci↗

arXiv2019

A General Deep Learning Framework for Network Reconstruction and Dynamics Learning

Many complex processes can be viewed as dynamical systems on networks. However, in real cases, only the performances of the system are known, the network structure and the dynamical rules are not observed. Therefore, recovering latent network structure and dynamics from observed time series data are important tasks because it may help us to open the black box, and even to build up the model of a complex system automatically. Although this problem hosts a wealth of potential applications in biology, earth science, and epidemics etc., conventional methods have limitations. In this work, we introduce a new framework, Gumbel Graph Network (GGN), which is a model-free, data-driven deep learning framework to accomplish the reconstruction of both network connections and the dynamics on it. Our model consists of two jointly trained parts: a network generator that generating a discrete network with the Gumbel Softmax technique; and a dynamics learner that utilizing the generated network and one-step trajectory value to predict the states in future steps. We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.

cond-mat.dis-nn↗

arXiv2019

Protection of Logical Qubits via Optimal State Transfers

Dynamical decoupling can enforce a symmetry on the dynamics of an open quantum system. Here we develop an efficient dynamical-decoupling-based strategy to create the decoherence-free subspaces (DFSs) for a set of qubits by optimally transferring the states of these qubits. We design to transfer the state of each qubit to all of the other qubits in an optimal and efficient manner, so as to produce an effective collective-type noise for all qubits. This collective pseudo-noise is essentially derived from arbitrarily independent real baths and needs only nearest-neighbor state transfers for its implementation. Moreover, our scheme requires only N steps to produce the effective collective-type noise for a system of N qubits. It provides an experimentally feasible and efficient approach to achieving the DFSs for encoding the protected logical qubits.

quant-ph↗

arXiv2018

Crowdsensing Game with Demand Uncertainties: A Deep Reinforcement Learning Approach

Currently, explosive increase of smartphones with powerful built-in sensors such as GPS, accelerometers, gyroscopes and cameras has made the design of crowdsensing applications possible, which create a new interface between human beings and life environment. Until now, various mobile crowdsensing applications have been designed, where the crowdsourcers can employ mobile users (MUs) to complete the required sensing tasks. In this paper, emerging learning-based techniques are leveraged to address crowdsensing game with demand uncertainties and private information protection of MUs. Firstly, a novel economic model for mobile crowdsensing is designed, which takes MUs' resources constraints and demand uncertainties into consideration. Secondly, an incentive mechanism based on Stackelberg game is provided, where the sensing-platform (SP) is the leader and the MUs are the followers. Then, the existence and uniqueness of the Stackelberg Equilibrium (SE) is proven and the procedure for computing the SE is given. Furthermore, a dynamic incentive mechanism (DIM) based on deep reinforcement learning (DRL) approach is investigated without knowing the private information of the MUs. It enables the SP to learn the optimal pricing strategy directly from game experience without any prior knowledge about MUs' information. Finally, numerical simulations are implemented to evaluate the performance and theoretical properties of the proposed mechanism and approach.

cs.CY↗

arXiv2018

A Novel Learning-based Global Path Planning Algorithm for Planetary Rovers

Autonomous path planning algorithms are significant to planetary exploration rovers, since relying on commands from Earth will heavily reduce their efficiency of executing exploration missions. This paper proposes a novel learning-based algorithm to deal with global path planning problem for planetary exploration rovers. Specifically, a novel deep convolutional neural network with double branches (DB-CNN) is designed and trained, which can plan path directly from orbital images of planetary surfaces without implementing environment mapping. Moreover, the planning procedure requires no prior knowledge about planetary surface terrains. Finally, experimental results demonstrate that DB-CNN achieves better performance on global path planning and faster convergence during training compared with the existing Value Iteration Network (VIN).

cs.CV↗

arXiv2018

Nonadiabatic holonomic quantum computation on coupled transmons with ancillaries

The physical implementation of holonomic quantum computation is challenging due to the needed complex controllable interactions in multilevel quantum systems. Here we propose to implement nonadiabatic holonomic quantum computation with conventional capacitive coupled superconducting transmon qubits. A universal set of holonomic gates is constructed with the help of the interaction with an auxiliary qubit rather than relying on delicate control over an auxiliary level of multilevel quantum systems. Explicitly, these quantum gates are realized by tunable interactions in an all-resonant way, which leads to high-fidelity gate operations. In this way, the distinct merit of our scheme is that we use only the lowest two levels of a transmon to form the qubit states. In addition, the auxiliary qubits are in their ground states before and after every gate operation, so that the holonomic gates can be constructed successively. Therefore, our scheme provides a promising method towards the practical realization of high-fidelity nonadiabatic holonomic quantum computation.

quant-ph↗

arXiv2018

A Novel Deep Neural Network Architecture for Mars Visual Navigation

In this paper, emerging deep learning techniques are leveraged to deal with Mars visual navigation problem. Specifically, to achieve precise landing and autonomous navigation, a novel deep neural network architecture with double branches and non-recurrent structure is designed, which can represent both global and local deep features of Martian environment images effectively. By employing this architecture, Mars rover can determine the optimal navigation policy to the target point directly from original Martian environment images. Moreover, compared with the existing state-of-the-art algorithm, the training time is reduced by 45.8%. Finally, experiment results demonstrate that the proposed deep neural network architecture achieves better performance and faster convergence than the existing ones and generalizes well to unknown environment.

cs.CV↗