arXiv subjects

Bo Wu

Publications and source records attributed to Bo Wu.

At least 163 records · Page 9Linked to original sources

arXiv2017

Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks

Prediction of popularity has profound impact for social media, since it offers opportunities to reveal individual preference and public attention from evolutionary social systems. Previous research, although achieves promising results, neglects one distinctive characteristic of social data, i.e., sequentiality. For example, the popularity of online content is generated over time with sequential post streams of social media. To investigate the sequential prediction of popularity, we propose a novel prediction framework called Deep Temporal Context Networks (DTCN) by incorporating both temporal context and temporal attention into account. Our DTCN contains three main components, from embedding, learning to predicting. With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space. Then, based on the embedded data sequence over time, temporal context learning attempts to recurrently learn two adaptive temporal contexts for sequential popularity. Finally, a novel temporal attention is designed to predict new popularity (the popularity of a new user-post pair) with temporal coherence across multiple time-scales. Experiments on our released image dataset with about 600K Flickr photos demonstrate that DTCN outperforms state-of-the-art deep prediction algorithms, with an average of 21.51% relative performance improvement in the popularity prediction (Spearman Ranking Correlation).

cs.SI↗

arXiv2017

Time Matters: Multi-scale Temporalization of Social Media Popularity

The evolution of social media popularity exhibits rich temporality, i.e., popularities change over time at various levels of temporal granularity. This is influenced by temporal variations of public attentions or user activities. For example, popularity patterns of street snap on Flickr are observed to depict distinctive fashion styles at specific time scales, such as season-based periodic fluctuations for Trench Coat or one-off peak in days for Evening Dress. However, this fact is often overlooked by existing research of popularity modeling. We present the first study to incorporate multiple time-scale dynamics into predicting online popularity. We propose a novel computational framework in the paper, named Multi-scale Temporalization, for estimating popularity based on multi-scale decomposition and structural reconstruction in a tensor space of user, post, and time by joint low-rank constraints. By considering the noise caused by context inconsistency, we design a data rearrangement step based on context aggregation as preprocessing to enhance contextual relevance of neighboring data in the tensor space. As a result, our approach can leverage multiple levels of temporal characteristics and reduce the noise of data decomposition to improve modeling effectiveness. We evaluate our approach on two large-scale Flickr image datasets with over 1.8 million photos in total, for the task of popularity prediction. The results show that our approach significantly outperforms state-of-the-art popularity prediction techniques, with a relative improvement of 10.9%-47.5% in terms of prediction accuracy.

cs.SI↗

arXiv2017

DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model

Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of the graph or key node neighborhoods of the graph into the same fixed form. During this transfer process, structural information of the graph can be lost, and some redundant information can be incorporated. To overcome this problem, we propose the disordered graph convolutional neural network (DGCNN) based on the mixed Gaussian model, which extends the CNN by adding a preprocessing layer called the disordered graph convolutional layer (DGCL). The DGCL uses a mixed Gaussian function to realize the mapping between the convolution kernel and the nodes in the neighborhood of the graph. The output of the DGCL is the input of the CNN. We further implement a backward-propagation optimization process of the convolutional layer by which we incorporate the feature-learning model of the irregular node neighborhood structure into the network. Thereafter, the optimization of the convolution kernel becomes part of the neural network learning process. The DGCNN can accept arbitrary scaled and disordered neighborhood graph structures as the receptive fields of CNNs, which reduces information loss during graph transformation. Finally, we perform experiments on multiple standard graph datasets. The results show that the proposed method outperforms the state-of-the-art methods in graph classification and retrieval.

cs.LG↗

arXiv2017

Pointwise Characterizations of Curvature and Second Fundamental Form on Riemannian Manifolds

Let $M$ be a complete Riemannian manifold possibly with a boundary $\partial M$. For any $C^1$-vector field $Z$, by using gradient/functional inequalities of the (reflecting) diffusion process generated by $L:=Δ+Z$, pointwise characterizations are presented for the Bakry-Emery curvature of $L$ and the second fundamental form of $\partial M$ if exists. These extend and strengthen the recent results derived by A. Naber for the uniform norm $\|{\mathbf{Ric}}_Z\|_\infty$ on manifolds without boundary. A key point of the present study is to apply the asymptotic formulas for these two tensors found by the first named author, such that the proofs are significantly simplified.

math.PR↗

arXiv2017

Learning Unified Embedding for Apparel Recognition

In apparel recognition, specialized models (e.g. models trained for a particular vertical like dresses) can significantly outperform general models (i.e. models that cover a wide range of verticals). Therefore, deep neural network models are often trained separately for different verticals. However, using specialized models for different verticals is not scalable and expensive to deploy. This paper addresses the problem of learning one unified embedding model for multiple object verticals (e.g. all apparel classes) without sacrificing accuracy. The problem is tackled from two aspects: training data and training difficulty. On the training data aspect, we figure out that for a single model trained with triplet loss, there is an accuracy sweet spot in terms of how many verticals are trained together. To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss. This new loss makes the training easier and make it possible for more efficient use of the feature space. The end result is a unified model which can achieve the same retrieval accuracy as a number of separate specialized models, while having the model complexity as one. The effectiveness of our approach is shown in experiments.

cs.CV↗

arXiv2017

Stochastic Heat Equations with Values in a Riemannian Manifold

The main result of this note is the existence of martingale solutions to the stochastic heat equation (SHE) in a Riemannian manifold by using suitable Dirichlet forms on the corresponding path/loop space. Moreover, we present some characterizations of the lower bound of the Ricci curvature by functional inequalities of various associated Dirichlet forms.

math.PR↗

arXiv2017

A Learning Based Optimal Human Robot Collaboration with Linear Temporal Logic Constraints

This paper considers an optimal task allocation problem for human robot collaboration in human robot systems with persistent tasks. Such human robot systems consist of human operators and intelligent robots collaborating with each other to accomplish complex tasks that cannot be done by either part alone. The system objective is to maximize the probability of successfully executing persistent tasks that are formulated as linear temporal logic specifications and minimize the average cost between consecutive visits of a particular proposition. This paper proposes to model the human robot collaboration under a framework with the composition of multiple Markov Decision Process (MDP) with possibly unknown transition probabilities, which characterizes how human cognitive states, such as human trust and fatigue, stochastically change with the robot performance. Under the unknown MDP models, an algorithm is developed to learn the model and obtain an optimal task allocation policy that minimizes the expected average cost for each task cycle and maximizes the probability of satisfying linear temporal logic constraints. Moreover, this paper shows that the difference between the optimal policy based on the learned model and that based on the underlying ground truth model can be bounded by arbitrarily small constant and large confidence level with sufficient samples. The case study of an assembly process demonstrates the effectiveness and benefits of our proposed learning based human robot collaboration.

cs.RO↗

arXiv2017

Communication-aware Motion Planning for Multi-agent Systems from Signal Temporal Logic Specifications

We propose a mathematical framework for synthesizing motion plans for multi-agent systems that fulfill complex, high-level and formal local specifications in the presence of inter-agent communication. The proposed synthesis framework consists of desired motion specifications in temporal logic (STL) formulas and a local motion controller that ensures the underlying agent not only to accomplish the local specifications but also to avoid collisions with other agents or possible obstacles, while maintaining an optimized communication quality of service (QoS) among the agents. Utilizing a Gaussian fading model for wireless communication channels, the framework synthesizes the desired motion controller by solving a joint optimization problem on motion planning and wireless communication, in which both the STL specifications and the wireless communication conditions are encoded as mixed integer-linear constraints on the variables of the agents' dynamical states and communication channel status. The overall framework is demonstrated by a case study of communication-aware multi-robot motion planning and the effectiveness of the framework is validated by simulation results.

eess.SY↗

arXiv2017

Distributed Communication-aware Motion Planning for Multi-agent Systems from STL and SpaTeL Specifications

In future intelligent transportation systems, networked vehicles coordinate with each other to achieve safe operations based on an assumption that communications among vehicles and infrastructure are reliable. Traditional methods usually deal with the design of control systems and communication networks in a separated manner. However, control and communication systems are tightly coupled as the motions of vehicles will affect the overall communication quality. Hence, we are motivated to study the co-design of both control and communication systems. In particular, we propose a control theoretical framework for distributed motion planning for multi-agent systems which satisfies complex and high-level spatial and temporal specifications while accounting for communication quality at the same time. Towards this end, desired motion specifications and communication performances are formulated as signal temporal logic (STL) and spatial-temporal logic (SpaTeL) formulas, respectively. The specifications are encoded as constraints on system and environment state variables of mixed integer linear programs (MILP), and upon which control strategies satisfying both STL and SpaTeL specifications are generated for each agent by employing a distributed model predictive control (MPC) framework. Effectiveness of the proposed framework is validated by a simulation of distributed communication-aware motion planning for multi-agent systems.

cs.MA↗

arXiv2017

Exactly solvable tight-binding models on two scale-free networks with identical degree distribution

We study ideal Bose gas upon two scale-free structures with identical degree distribution. Energy spectra belonging to tight-binding Hamiltonian are exactly solved and the related spectral dimensions of $G_1$ and $ G_2$ are obtained as $d_{s_1} = 2$ and $d_{s_2} = 2 \ln 4/ \ln 3$. We show Bose-Einstein condensation will only take place upon $G_2$ instead of $G_1$. The topology and thermodynamical property of the two structures are proven to be totally different.

cond-mat.quant-gas↗

arXiv2017

Feature Selection Parallel Technique for Remotely Sensed Imagery Classification

Remote sensing research focusing on feature selection has long attracted the attention of the remote sensing community because feature selection is a prerequisite for image processing and various applications. Different feature selection methods have been proposed to improve the classification accuracy. They vary from basic search techniques to clonal selections, and various optimal criteria have been investigated. Recently, methods using dependence-based measures have attracted much attention due to their ability to deal with very high dimensional datasets. However, these methods are based on Cramers V test, which has performance issues with large datasets. In this paper, we propose a parallel approach to improve their performance. We evaluate our approach on hyper-spectral and high spatial resolution images and compare it to the proposed methods with a centralized version as preliminary results. The results are very promising.

cs.DC↗

arXiv2017

Supervisor Synthesis of POMDP based on Automata Learning

As a general and thus popular model for autonomous systems, partially observable Markov decision process (POMDP) can capture uncertainties from different sources like sensing noises, actuation errors, and uncertain environments. However, its comprehensiveness makes the planning and control in POMDP difficult. Traditional POMDP planning problems target to find the optimal policy to maximize the expectation of accumulated rewards. But for safety critical applications, guarantees of system performance described by formal specifications are desired, which motivates us to consider formal methods to synthesize supervisor for POMDP. With system specifications given by Probabilistic Computation Tree Logic (PCTL), we propose a supervisory control framework with a type of deterministic finite automata (DFA), za-DFA, as the controller form. While the existing work mainly relies on optimization techniques to learn fixed-size finite state controllers (FSCs), we develop an $L^*$ learning based algorithm to determine both space and transitions of za-DFA. Membership queries and different oracles for conjectures are defined. The learning algorithm is sound and complete. An example is given in detailed steps to illustrate the supervisor synthesis algorithm.

eess.SY↗

arXiv2017

Permissive Supervisor Synthesis for Markov Decision Processes through Learning

This paper considers the permissive supervisor synthesis for probabilistic systems modeled as Markov Decision Processes (MDP). Such systems are prevalent in power grids, transportation networks, communication networks and robotics. Unlike centralized planning and optimization based planning, we propose a novel supervisor synthesis framework based on learning and compositional model checking to generate permissive local supervisors in a distributed manner. With the recent advance in assume-guarantee reasoning verification for probabilistic systems, building the composed system can be avoided to alleviate the state space explosion and our framework learn the supervisors iteratively based on the counterexamples from verification. Our approach is guaranteed to terminate in finite steps and to be correct.

cs.LO↗

arXiv2017

Counterexample-guided Abstraction Refinement for POMDPs

Partially Observable Markov Decision Process (POMDP) is widely used to model probabilistic behavior for complex systems. Compared with MDPs, POMDP models a system more accurate but solving a POMDP generally takes exponential time in the size of its state space. This makes the formal verification and synthesis problems much more challenging for POMDPs, especially when multiple system components are involved. As a promising technique to reduce the verification complexity, the abstraction method tries to find an abstract system with a smaller state space but preserves enough properties for the verification purpose. While abstraction based verification has been explored extensively for MDPs, in this paper, we present the first result of POMDP abstraction and its refinement techniques. The main idea follows the counterexample-guided abstraction refinement (CEGAR) framework. Starting with a coarse guess for the POMDP abstraction, we iteratively use counterexamples from formal verification to refine the abstraction until the abstract system can be used to infer the verification result for the original POMDP. Our main contributions have two folds: 1) we propose a novel abstract system model for POMDP and a new simulation relation to capture the partial observability then prove the preservation on a fragment of Probabilistic Computation Tree Logic (PCTL); 2) to find a proper abstract system that can prove or disprove the satisfaction relation on the concrete POMDP, we develop a novel refinement algorithm. Our work leads to a sound and complete CEGAR framework for POMDP.

cs.LO↗

arXiv2016

Formal Design of Robot Integrated Task and Motion Planning

Integrated Task and Motion Planning (ITMP) for mobile robots in a dynamic environment with moving obstacles is a challenging research question and attracts more and more attentions recently. Most existing methods either restrict to static environments or lack performance guarantees. This motivates us to investigate the ITMP problem using formal methods and propose a bottom-up compositional design approach called CoSMoP (Composition of Safe Motion Primitives). Our basic idea is to synthesize a global motion plan through composing simple local moves and actions, and to achieve its performance guarantee through modular and incremental verifications. The design consists of two steps. First, basic motion primitives are designed and verified locally. Then, a global motion path is built upon these certified motion primitives by concatenating them together. In particular, we model the motion primitives as hybrid automata and verify their safety through formulating as Differential Dynamic Logic (d$\mathcal{L}$). Furthermore, these proven safe motion primitives are composed based on an encoding to Satisfiability Modulo Theories (SMT) that takes into account the geometric constraints. Since d$\mathcal{L}$ allows compositional verification, the sequential composition of the safe motion primitives also preserves safety properties. Therefore, the CoSMoP generates correct plans for given task specifications that are formally proven safe even for moving obstacles. Illustrative examples are presented to show the effectiveness of the methods.

cs.RO↗

arXiv2016

Combined Top-Down and Bottom-Up Approaches to Performance-guaranteed Integrated Task and Motion Planning of Cooperative Multi-agent Systems

We propose a hierarchical design framework to automatically synthesize coordination schemes and control policies for cooperative multi-agent systems to fulfill formal performance requirements, by associating a bottom-up reactive motion controller with a top-down mission plan. On one hand, starting from a global mission that is specified as a regular language over all the agents' mission capabilities, a mission planning layer sits on the top of the proposed framework, decomposing the global mission into local tasks that are in consistency with each agent's individual capabilities, and compositionally justifying whether the achievement of local tasks implies the satisfaction of the global mission via an assume-guarantee paradigm. On the other hand, bottom-up motion plans associated with each agent are synthesized corresponding to the obtained local missions by composing basic motion primitives, which are verified safe by differential dynamic logic (d$\mathcal{L}$), through a Satisfiability Modulo Theories (SMT) solver that searches feasible solutions in face of constraints imposed by local task requirements and the environment description. It is shown that the proposed framework can handle dynamical environments as the motion primitives possess reactive features, making the motion plans adaptive to local environmental changes. Furthermore, on-line mission reconfiguration can be triggered by the motion planning layer once no feasible solutions can be found through the SMT solver. The effectiveness of the overall design framework is validated by an automated warehouse case study.

cs.RO↗

arXiv2016

Characterizing the path-independent property of the Girsanov density for degenerated stochastic differential equations

In this paper, we derive a characterization theorem for the path-independent property of the density of the Girsanov transformation for {\it degenerated} stochastic differential equations (SDEs), extending the characterization theorem of \cite{twwy} for the non-degenerated SDEs. We further extends our consideration to non-Lipschitz SDEs with jumps and with degenerated diffusion coefficients, which generalizes the corresponding characterization theorem established in \cite{hqwu}.

math.PR↗

arXiv2016

Bibliometric Index for Academic Leadership

Academic leadership is essential for research innovation and impact. Until now, there has been no dedicated measure of leadership by bibliometrics. Popular bibliometric indices are mainly based on academic output, such as the journal impact factor and the number of citations. Here we develop an academic leadership index based on readily available bibliometric data that is sensitive to not only academic output but also research efficiency. Our leadership index was tested in two studies on peer-reviewed journal papers by extramurally-funded principal investigators in the field of life sciences from China and the USA, respectively. The leadership performance of these principal investigators was quantified and compared relative to university rank and other factors. As a validation measure, we show that the highest average leadership index was achieved by principal investigators at top national universities in both countries. More interestingly, our results also indicate that on an individual basis, strong leadership and high efficiency are not necessarily associated with those at top-tier universities nor with the most funding. This leadership index may become the basis of a comprehensive merit system, facilitating academic evaluation and resource management.

cs.DL↗