arXiv subjects

Qi Zhu

Publications and source records attributed to Qi Zhu.

At least 235 records · Page 13Linked to original sources

arXiv2020

Cross-Layer Design of Automotive Systems

With growing system complexity and closer cyber-physical interaction, there are increasingly stronger dependencies between different function and architecture layers in automotive systems. This paper first introduces several cross-layer approaches we developed in the past for holistically addressing multiple system layers in the design of individual vehicles and of connected vehicle applications; and then presents a new methodology based on the weakly-hard paradigm for leveraging the scheduling flexibility in architecture layer to improve the system performance at function layer. The results of these works demonstrate the importance and effectiveness of cross-layer design for automotive systems.

eess.SY↗

arXiv2020

Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation

There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations. Although many methods are devised to evaluate and improve the performance of individual dialog components, there is a lack of comprehensive empirical study on how different components contribute to the overall performance of a dialog system. In this paper, we perform a system-wise evaluation and present an empirical analysis on different types of dialog systems which are composed of different modules in different settings. Our results show that (1) a pipeline dialog system trained using fine-grained supervision signals at different component levels often obtains better performance than the systems that use joint or end-to-end models trained on coarse-grained labels, (2) component-wise, single-turn evaluation results are not always consistent with the overall performance of a dialog system, and (3) despite the discrepancy between simulators and human users, simulated evaluation is still a valid alternative to the costly human evaluation especially in the early stage of development.

cs.CL↗

arXiv2020

SAW: A Tool for Safety Analysis of Weakly-hard Systems

We introduce SAW, a tool for safety analysis of weakly-hard systems, in which traditional hard timing constraints are relaxed to allow bounded deadline misses for improving design flexibility and runtime resiliency. Safety verification is a key issue for weakly-hard systems, as it ensures system safety under allowed deadline misses. Previous works are either for linear systems only, or limited to a certain type of nonlinear systems (e.g., systems that satisfy exponential stability and Lipschitz continuity of the system dynamics). In this work, we propose a new technique for infinite-time safety verification of general nonlinear weakly-hard systems. Our approach first discretizes the safe state set into grids and constructs a directed graph, where nodes represent the grids and edges represent the reachability relation. Based on graph theory and dynamic programming, our approach can effectively find the safe initial set (consisting of a set of grids), from which the system can be proven safe under given weakly-hard constraints. Experimental results demonstrate the effectiveness of our approach, when compared with the state-of-the-art. An open source implementation of our tool is available at https://github.com/551100kk/SAW. The virtual machine where the tool is ready to run can be found at https://www.csie.ntu.edu.tw/~r08922054/SAW.ova.

eess.SY↗

arXiv2020

Opportunistic Intermittent Control with Safety Guarantees for Autonomous Systems

Control schemes for autonomous systems are often designed in a way that anticipates the worst case in any situation. At runtime, however, there could exist opportunities to leverage the characteristics of specific environment and operation context for more efficient control. In this work, we develop an online intermittent-control framework that combines formal verification with model-based optimization and deep reinforcement learning to opportunistically skip certain control computation and actuation to save actuation energy and computational resources without compromising system safety. Experiments on an adaptive cruise control system demonstrate that our approach can achieve significant energy and computation savings.

eess.SY↗

arXiv2020

Facet-Aware Evaluation for Extractive Summarization

Commonly adopted metrics for extractive summarization focus on lexical overlap at the token level. In this paper, we present a facet-aware evaluation setup for better assessment of the information coverage in extracted summaries. Specifically, we treat each sentence in the reference summary as a \textit{facet}, identify the sentences in the document that express the semantics of each facet as \textit{support sentences} of the facet, and automatically evaluate extractive summarization methods by comparing the indices of extracted sentences and support sentences of all the facets in the reference summary. To facilitate this new evaluation setup, we construct an extractive version of the CNN/Daily Mail dataset and perform a thorough quantitative investigation, through which we demonstrate that facet-aware evaluation manifests better correlation with human judgment than ROUGE, enables fine-grained evaluation as well as comparative analysis, and reveals valuable insights of state-of-the-art summarization methods. Data can be found at https://github.com/morningmoni/FAR.

cs.CL↗

arXiv2020

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab (Lee et al., 2019b), ConvLab-2 inherits ConvLab's framework but integrates more powerful dialogue models and supports more datasets. Besides, we have developed an analysis tool and an interactive tool to assist researchers in diagnosing dialogue systems. The analysis tool presents rich statistics and summarizes common mistakes from simulated dialogues, which facilitates error analysis and system improvement. The interactive tool provides a user interface that allows developers to diagnose an assembled dialogue system by interacting with the system and modifying the output of each system component.

cs.CL↗

arXiv2020

CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset. It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. Moreover, the corpus contains rich annotation of dialogue states and dialogue acts at both user and system sides. About 60% of the dialogues have cross-domain user goals that favor inter-domain dependency and encourage natural transition across domains in conversation. We also provide a user simulator and several benchmark models for pipelined task-oriented dialogue systems, which will facilitate researchers to compare and evaluate their models on this corpus. The large size and rich annotation of CrossWOZ make it suitable to investigate a variety of tasks in cross-domain dialogue modeling, such as dialogue state tracking, policy learning, user simulation, etc.

cs.CL↗

arXiv2020

Trajectory Planning for Connected and Automated Vehicles: Cruising, Lane Changing, and Platooning

Autonomy and connectivity are considered among the most promising technologies to improve safety, mobility, fuel and time consumption in transportation systems. Some of the fuel efficiency benefits of connected and automated vehicles (CAVs) can be realized through platooning. A platoon is a virtual train of CAVs that travel together following the platoon head, with small gaps between them. Vehicles may also reduce travel time by lane changing. In this paper, we devise an optimal control-based trajectory planning model that can provide safe and efficient trajectories for the subject vehicle and can incorporate platooning and lane changing. We embed this trajectory planning model in a simulation framework to quantify its efficiency benefits as it relates to fuel consumption and travel time, in a dynamic traffic stream. Furthermore, we perform extensive numerical experiments to investigate whether, and the circumstances under which, the vehicles in upstream of the subject vehicle may also experience second-hand fuel efficiency benefits.

cs.RO↗

arXiv2019

Eavesdrop the Composition Proportion of Training Labels in Federated Learning

Federated learning (FL) has recently emerged as a new form of collaborative machine learning, where a common model can be learned while keeping all the training data on local devices. Although it is designed for enhancing the data privacy, we demonstrated in this paper a new direction in inference attacks in the context of FL, where valuable information about training data can be obtained by adversaries with very limited power. In particular, we proposed three new types of attacks to exploit this vulnerability. The first type of attack, Class Sniffing, can detect whether a certain label appears in training. The other two types of attacks can determine the quantity of each label, i.e., Quantity Inference attack determines the composition proportion of the training label owned by the selected clients in a single round, while Whole Determination attack determines that of the whole training process. We evaluated our attacks on a variety of tasks and datasets with different settings, and the corresponding results showed that our attacks work well generally. Finally, we analyzed the impact of major hyper-parameters to our attacks and discussed possible defenses.

cs.LG↗

arXiv2019

MaskPlus: Improving Mask Generation for Instance Segmentation

Instance segmentation is a promising yet challenging topic in computer vision. Recent approaches such as Mask R-CNN typically divide this problem into two parts -- a detection component and a mask generation branch, and mostly focus on the improvement of the detection part. In this paper, we present an approach that extends Mask R-CNN with five novel optimization techniques for improving the mask generation branch and reducing the conflicts between the mask branch and the detection component in training. These five techniques are independent to each other and can be flexibly utilized in building various instance segmentation architectures for increasing the overall accuracy. We demonstrate the effectiveness of our approach with tests on the COCO dataset.

cs.CV↗

arXiv2019

Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity

Text-rich heterogeneous information networks (text-rich HINs) are ubiquitous in real-world applications. Hypernymy, also known as is-a relation or subclass-of relation, lays in the core of many knowledge graphs and benefits many downstream applications. Existing methods of hypernymy discovery either leverage textual patterns to extract explicitly mentioned hypernym-hyponym pairs, or learn a distributional representation for each term of interest based its context. These approaches rely on statistical signals from the textual corpus, and their effectiveness would therefore be hindered when the signals from the corpus are not sufficient for all terms of interest. In this work, we propose to discover hypernymy in text-rich HINs, which can introduce additional high-quality signals. We develop a new framework, named HyperMine, that exploits multi-granular contexts and combines signals from both text and network without human labeled data. HyperMine extends the definition of context to the scenario of text-rich HIN. For example, we can define typed nodes and communities as contexts. These contexts encode signals of different granularities and we feed them into a hypernymy inference model. HyperMine learns this model using weak supervision acquired based on high-precision textual patterns. Extensive experiments on two large real-world datasets demonstrate the effectiveness of HyperMine and the utility of modeling context granularity. We further show a case study that a high-quality taxonomy can be generated solely based on the hypernymy discovered by HyperMine.

cs.CL↗

arXiv2019

Task-Guided Pair Embedding in Heterogeneous Network

Many real-world tasks solved by heterogeneous network embedding methods can be cast as modeling the likelihood of pairwise relationship between two nodes. For example, the goal of author identification task is to model the likelihood of a paper being written by an author (paper-author pairwise relationship). Existing task-guided embedding methods are node-centric in that they simply measure the similarity between the node embeddings to compute the likelihood of a pairwise relationship between two nodes. However, we claim that for task-guided embeddings, it is crucial to focus on directly modeling the pairwise relationship. In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e.g., paper-author relationship in author identification). To this end, we 1) propose to learn a pair embedding under the guidance of its associated context path, i.e., a sequence of nodes between the pair, and 2) devise the pair validity classifier to distinguish whether the pair is valid with respect to the specific task at hand. By introducing pair embeddings that capture the semantics behind the pairwise relationships, we are able to learn the fine-grained pairwise relationship between two nodes, which is paramount for task-guided embedding methods. Extensive experiments on author identification task demonstrate that TaPEm outperforms the state-of-the-art methods, especially for authors with few publication records.

cs.CL↗

arXiv2019

Metal Object Detection Based on Load Impedance and Input Power Characteristics for High-dimensional WPT System

High-dimensional wireless power transfer (WPT) systems have received increasing attention for charging mobile devices. With the receivers have higher spatial freedom, the systems are more susceptible to the metal objects in the surroundings. However, conventional methods for metal object detection (MOD) can't satisfy the requirements of safety and stability of new systems. This paper proposed a metal detection method which is more suitable for high-dimensional WPT systems. The key feature of the proposed method is combining load impedance and input power characteristics curves to determine whether the receiver is a metal object or a coil. And the influence of the metal is discussed in the circuit and magnetic model. The method is theoretically proven by the simulation calculation. And the experiments verified that the method can accurately detect the metal objects by setting the threshold curves.

eess.SP↗

arXiv2019

ReachNN: Reachability Analysis of Neural-Network Controlled Systems

Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural-network controllers in the loop. Previous methods for verifying neural network controlled systems are limited to a few specific activation functions. In this work, we propose a new reachability analysis approach based on Bernstein polynomials that can verify neural-network controlled systems with a more general form of activation functions, i.e., as long as they ensure that the neural networks are Lipschitz continuous. Specifically, we consider abstracting feedforward neural networks with Bernstein polynomials for a small subset of inputs. To quantify the error introduced by abstraction, we provide both theoretical error bound estimation based on the theory of Bernstein polynomials and more practical sampling based error bound estimation, following a tight Lipschitz constant estimation approach based on forward reachability analysis. Compared with previous methods, our approach addresses a much broader set of neural networks, including heterogeneous neural networks that contain multiple types of activation functions. Experiment results on a variety of benchmarks show the effectiveness of our approach.

eess.SY↗

arXiv2019

Effect of Surrounding Conductive Object on Four-Plate Capacitive Power Transfer System

In this paper, the effect of a surrounding conductive object on a typical capacitive power transfer (CPT) system with two pairs of parallel plates is studied by considering the mutual coupling between the conductive object and the plates. A mathematical model is established based on a 5*5 mutual capacitance matrix by using a larger additional conductive plate to represent the surrounding conductive object. Based on the proposed model, the effect of the additional conductive plate on the CPT system is analyzed in detail. The electric field distribution of the CPT system including the additional plate is simulated by ANSYS Maxwell. A practical CPT system consisting of four 100mm*100mm square aluminum plates and one 300mm*300mm square aluminum plate is built to verify the modeling and analysis. Both theoretical and experimental results show that the output voltage of the CPT system decreases when the additional conductive plate is placed closer to the CPT system. It has found that the additional plate can effectively shield the electric field outside the plate, and it attracts the electric field in-between the four plates of the CPT system and the additional plate. It has also found that the voltage potential difference between the additional plate and the reference plate of the CPT system remains almost constant even when the distance between them changes. The findings are useful for guiding the design of CPT systems, particularly the electric field shielding.

physics.app-ph↗

arXiv2019

ConvLab: Multi-Domain End-to-End Dialog System Platform

We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings.

cs.CL↗

arXiv2018

Integrating Local Context and Global Cohesiveness for Open Information Extraction

Extracting entities and their relations from text is an important task for understanding massive text corpora. Open information extraction (IE) systems mine relation tuples (i.e., entity arguments and a predicate string to describe their relation) from sentences. These relation tuples are not confined to a predefined schema for the relations of interests. However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions. In this paper, we propose a novel Open IE system, called ReMine, which integrates local context signals and global structural signals in a unified, distant-supervision framework. Leveraging facts from external knowledge bases as supervision, the new system can be applied to many different domains to facilitate sentence-level tuple extractions using corpus-level statistics. Our system operates by solving a joint optimization problem to unify (1) segmenting entity/relation phrases in individual sentences based on local context; and (2) measuring the quality of tuples extracted from individual sentences with a translating-based objective. Learning the two subtasks jointly helps correct errors produced in each subtask so that they can mutually enhance each other. Experiments on two real-world corpora from different domains demonstrate the effectiveness, generality, and robustness of ReMine when compared to state-of-the-art open IE systems.

cs.CL↗

arXiv2018

Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. In the meantime, network embedding has emerged as a convenient tool to mine and learn from networked data. As a result, it is of interest to develop HIN embedding methods. However, the heterogeneity in HINs introduces not only rich information but also potentially incompatible semantics, which poses special challenges to embedding learning in HINs. With the intention to preserve the rich yet potentially incompatible information in HIN embedding, we propose to study the problem of comprehensive transcription of heterogeneous information networks. The comprehensive transcription of HINs also provides an easy-to-use approach to unleash the power of HINs, since it requires no additional supervision, expertise, or feature engineering. To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics. To corroborate the efficacy of HEER, we conducted experiments on two large-scale real-words datasets with an edge reconstruction task and multiple case studies. Experiment results demonstrate the effectiveness of the proposed HEER model and the utility of edge representations and heterogeneous metrics. The code and data are available at https://github.com/GentleZhu/HEER.

cs.SI↗