arXiv subjects

Guan Wang

Publications and source records attributed to Guan Wang.

At least 73 records · Page 4Linked to original sources

arXiv2023

AaKOS: Aspect-adaptive Knowledge-based Opinion Summarization

The rapid growth of information on the Internet has led to an overwhelming amount of opinions and comments on various activities, products, and services. This makes it difficult and time-consuming for users to process all the available information when making decisions. Text summarization, a Natural Language Processing (NLP) task, has been widely explored to help users quickly retrieve relevant information by generating short and salient content from long or multiple documents. Recent advances in pre-trained language models, such as ChatGPT, have demonstrated the potential of Large Language Models (LLMs) in text generation. However, LLMs require massive amounts of data and resources and are challenging to implement as offline applications. Furthermore, existing text summarization approaches often lack the ``adaptive" nature required to capture diverse aspects in opinion summarization, which is particularly detrimental to users with specific requirements or preferences. In this paper, we propose an Aspect-adaptive Knowledge-based Opinion Summarization model for product reviews, which effectively captures the adaptive nature required for opinion summarization. The model generates aspect-oriented summaries given a set of reviews for a particular product, efficiently providing users with useful information on specific aspects they are interested in, ensuring the generated summaries are more personalized and informative. Extensive experiments have been conducted using real-world datasets to evaluate the proposed model. The results demonstrate that our model outperforms state-of-the-art approaches and is adaptive and efficient in generating summaries that focus on particular aspects, enabling users to make well-informed decisions and catering to their diverse interests and preferences.

cs.CL↗

arXiv2023

Instance-Variant Loss with Gaussian RBF Kernel for 3D Cross-modal Retriveal

3D cross-modal retrieval is gaining attention in the multimedia community. Central to this topic is learning a joint embedding space to represent data from different modalities, such as images, 3D point clouds, and polygon meshes, to extract modality-invariant and discriminative features. Hence, the performance of cross-modal retrieval methods heavily depends on the representational capacity of this embedding space. Existing methods treat all instances equally, applying the same penalty strength to instances with varying degrees of difficulty, ignoring the differences between instances. This can result in ambiguous convergence or local optima, severely compromising the separability of the feature space. To address this limitation, we propose an Instance-Variant loss to assign different penalty strengths to different instances, improving the space separability. Specifically, we assign different penalty weights to instances positively related to their intra-class distance. Simultaneously, we reduce the cross-modal discrepancy between features by learning a shared weight vector for the same class data from different modalities. By leveraging the Gaussian RBF kernel to evaluate sample similarity, we further propose an Intra-Class loss function that minimizes the intra-class distance among same-class instances. Extensive experiments on three 3D cross-modal datasets show that our proposed method surpasses recent state-of-the-art approaches.

cs.CV↗

arXiv2023

Interactive Learning from Policy-Dependent Human Feedback

This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide feedback for decisions that is dependent on the behavior they are teaching and is independent from the learner's current policy. We present empirical results that show this assumption to be false -- whether human trainers give a positive or negative feedback for a decision is influenced by the learner's current policy. Based on this insight, we introduce {\em Convergent Actor-Critic by Humans} (COACH), an algorithm for learning from policy-dependent feedback that converges to a local optimum. Finally, we demonstrate that COACH can successfully learn multiple behaviors on a physical robot.

cs.AI↗

arXiv2022

KATSum: Knowledge-aware Abstractive Text Summarization

Text Summarization is recognised as one of the NLP downstream tasks and it has been extensively investigated in recent years. It can assist people with perceiving the information rapidly from the Internet, including news articles, social posts, videos, etc. Most existing research works attempt to develop summarization models to produce a better output. However, advent limitations of most existing models emerge, including unfaithfulness and factual errors. In this paper, we propose a novel model, named as Knowledge-aware Abstractive Text Summarization, which leverages the advantages offered by Knowledge Graph to enhance the standard Seq2Seq model. On top of that, the Knowledge Graph triplets are extracted from the source text and utilised to provide keywords with relational information, producing coherent and factually errorless summaries. We conduct extensive experiments by using real-world data sets. The results reveal that the proposed framework can effectively utilise the information from Knowledge Graph and significantly reduce the factual errors in the summary.

cs.CL↗

arXiv2022

PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection

3D object detection is a critical task in autonomous driving. Recently multi-modal fusion-based 3D object detection methods, which combine the complementary advantages of LiDAR and camera, have shown great performance improvements over mono-modal methods. However, so far, no methods have attempted to utilize the instance-level contextual image semantics to guide the 3D object detection. In this paper, we propose a simple and effective Painting Adaptive Instance-prior for 3D object detection (PAI3D) to fuse instance-level image semantics flexibly with point cloud features. PAI3D is a multi-modal sequential instance-level fusion framework. It first extracts instance-level semantic information from images, the extracted information, including objects categorical label, point-to-object membership and object position, are then used to augment each LiDAR point in the subsequent 3D detection network to guide and improve detection performance. PAI3D outperforms the state-of-the-art with a large margin on the nuScenes dataset, achieving 71.4 in mAP and 74.2 in NDS on the test split. Our comprehensive experiments show that instance-level image semantics contribute the most to the performance gain, and PAI3D works well with any good-quality instance segmentation models and any modern point cloud 3D encoders, making it a strong candidate for deployment on autonomous vehicles.

cs.CV↗

arXiv2022

Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing

The explosion of e-commerce has caused the need for processing and analysis of product titles, like entity typing in product titles. However, the rapid activity in e-commerce has led to the rapid emergence of new entities, which is difficult to be solved by general entity typing. Besides, product titles in e-commerce have very different language styles from text data in general domain. In order to handle new entities in product titles and address the special language styles problem of product titles in e-commerce domain, we propose our textual entailment model with continuous prompt tuning based hypotheses and fusion embeddings for e-commerce entity typing. First, we reformulate the entity typing task into a textual entailment problem to handle new entities that are not present during training. Second, we design a model to automatically generate textual entailment hypotheses using a continuous prompt tuning method, which can generate better textual entailment hypotheses without manual design. Third, we utilize the fusion embeddings of BERT embedding and CharacterBERT embedding with a two-layer MLP classifier to solve the problem that the language styles of product titles in e-commerce are different from that of general domain. To analyze the effect of each contribution, we compare the performance of entity typing and textual entailment model, and conduct ablation studies on continuous prompt tuning and fusion embeddings. We also evaluate the impact of different prompt template initialization for the continuous prompt tuning. We show our proposed model improves the average F1 score by around 2% compared to the baseline BERT entity typing model.

cs.CL↗

arXiv2022

Indoor optical fiber eavesdropping approach and its avoidance

The optical fiber network has become a worldwide infrastructure. In addition to the basic functions in telecommunication, its sensing ability has attracted more and more attention. In this paper, we discuss the risk of household fiber being used for eavesdropping and demonstrate its performance in the lab. Using a 3-meter tail fiber in front of the household optical modem, voices of normal human speech can be eavesdropped by a laser interferometer and recovered 1.1 km away. The detection distance limit and system noise are analyzed quantitatively. We also give some practical ways to prevent eavesdropping through household fiber.

cs.SD↗

arXiv2022

KubeAdaptor: A Docking Framework for Workflow Containerization on Kubernetes

As Kubernetes becomes the infrastructure of the cloud-native era, the integration of workflow systems with Kubernetes is gaining more and more popularity. To our knowledge, workflow systems employ scheduling algorithms that optimize task execution order of workflow to improve performance and execution efficiency. However, due to its inherent scheduling mechanism, Kubernetes does not execute containerized scheduling following the optimized task execution order of workflow amid migrating workflow systems to the Kubernetes platform. This inconsistency in task scheduling order seriously degrades the efficiency of workflow execution and brings numerous challenges to the containerized process of workflow systems on Kubernetes. In this paper, we propose a cloud-native workflow engine, also known as KubeAdaptor, a docking framework able to implement workflow containerization on Kubernetes, integrate workflow systems with Kubernetes, ensuring the consistency of task scheduling order. We introduce the design and architecture of the KubeAdaptor, elaborate on the functionality implementation and the event-trigger mechanism within the KubeAdaptor. Experimental results about four real-world workflows show that the KubeAdaptor ensures the consistency of the workflow systems and Kubernetes in the task scheduling order. Compared with the baseline Argo workflow engine, the KubeAdaptor achieves better performance in terms of the average execution time of task pod, average workflow lifecycle, and resource usage rate.

cs.DC↗

arXiv2022

Epicenter localization using forward-transmission laser interferometry

Widely distributed optical fibers, together with phase-sensitive laser interferometry, can expand seismic detection methods and have great potential for epicenter localization. In this paper, we propose an integral response method based on a forward transmission scheme. It uses spectrum analysis and parameter fitting to localize the epicenter. With the given shape of the fiber ring, the integral phase changes of light propagating in the forward and reverse directions can be used to determine the direction, depth, distance of the epicenter, and seismic wave speed. For the noisy case with SNR=20 dB, the simulation results show ultrahigh precision when epicenter distance is 200 km: the error of the orientation angle is ~0.003°, the error of the P-wave speed is ~0.9 m/s, the error of the epicenter depth is ~9.5 m, and the error of the epicenter distance is ~200 m.

physics.ins-det↗

arXiv2022

A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving

Heated debates continue over the best autonomous driving framework. The classic modular pipeline is widely adopted in the industry owing to its great interpretability and stability, whereas the fully end-to-end paradigm has demonstrated considerable simplicity and learnability along with the rise of deep learning. As a way of marrying the advantages of both approaches, learning a semantically meaningful representation and then use in the downstream driving policy learning tasks provides a viable and attractive solution. However, several key challenges remain to be addressed, including identifying the most effective representation, alleviating the sim-to-real generalization issue as well as balancing model training cost. In this study, we propose a versatile and efficient reinforcement learning framework and build a fully functional autonomous vehicle for real-world validation. Our framework shows great generalizability to various complicated real-world scenarios and superior training efficiency against the competing baselines.

cs.RO↗

arXiv2022

Meta-learning with GANs for anomaly detection, with deployment in high-speed rail inspection system

Anomaly detection has been an active research area with a wide range of potential applications. Key challenges for anomaly detection in the AI era with big data include lack of prior knowledge of potential anomaly types, highly complex and noisy background in input data, scarce abnormal samples, and imbalanced training dataset. In this work, we propose a meta-learning framework for anomaly detection to deal with these issues. Within this framework, we incorporate the idea of generative adversarial networks (GANs) with appropriate choices of loss functions including structural similarity index measure (SSIM). Experiments with limited labeled data for high-speed rail inspection demonstrate that our meta-learning framework is sharp and robust in identifying anomalies. Our framework has been deployed in five high-speed railways of China since 2021: it has reduced more than 99.7% workload and saved 96.7% inspection time.

cs.LG↗

arXiv2022

Time shifting deviation method enhanced laser interferometry: ultrahigh precision localizing of traffic vibration using urban fiber link

Using fiber network as a huge sensing system will enrich monitoring methods of public infrastructures and geological disasters. With traditional cross-correlation method, laser interferometer has been used to detect and localize the vibration event. However, the random error induced by cross-correlation method limits the localization accuracy, and makes it not suitable for ultrahigh precision localizing applications. We propose a novel time shifting deviation (TSDEV) method, which has advantages over cross-correlation method in practicability and localization accuracy. Three experiments are carried out to demonstrate the novelty of the TSDEV method. In lab test, vibration localization accuracy of ~2.5 m is realized. In field tests, TSDEV method enhanced interferometry is applied to monitor the urban fiber link. Traffic vibration events on the campus road and Beijing ring road have been precisely localized and analyzed, respectively. The proposed technique will extend the function of existing urban fiber network, and better serve the future smart city.

physics.ins-det↗

arXiv2022

Transfer Learning for Retinal Vascular Disease Detection: A Pilot Study with Diabetic Retinopathy and Retinopathy of Prematurity

Retinal vascular diseases affect the well-being of human body and sometimes provide vital signs of otherwise undetected bodily damage. Recently, deep learning techniques have been successfully applied for detection of diabetic retinopathy (DR). The main obstacle of applying deep learning techniques to detect most other retinal vascular diseases is the limited amount of data available. In this paper, we propose a transfer learning technique that aims to utilize the feature similarities for detecting retinal vascular diseases. We choose the well-studied DR detection as a source task and identify the early detection of retinopathy of prematurity (ROP) as the target task. Our experimental results demonstrate that our DR-pretrained approach dominates in all metrics the conventional ImageNet-pretrained transfer learning approach, currently adopted in medical image analysis. Moreover, our approach is more robust with respect to the stochasticity in the training process and with respect to reduced training samples. This study suggests the potential of our proposed transfer learning approach for a broad range of retinal vascular diseases or pathologies, where data is limited.

cs.LG↗

arXiv2021

Fast Subspace Identification Method Based on Containerised Cloud Workflow Processing System

Subspace identification (SID) has been widely used in system identification and control fields since it can estimate system models only relying on the input and output data by reliable numerical operations such as singular value decomposition (SVD). However, high-dimension Hankel matrices are involved to store these data and used to obtain the system models, which increases the computation amount of SID and leads SID not suitable for the large-scale or real-time identification tasks. In this paper, a novel fast SID method based on cloud workflow processing and container technology is proposed to accelerate the traditional algorithm. First, a workflow-based structure of SID is designed to match the distributed cloud environment, based on the computational feature of each calculation stage. Second, a containerised cloud workflow processing system is established to execute the logic- and data- dependent SID workflow mission based on Kubernetes system. Finally, the experiments show that the computation time is reduced by at most $91.6\%$ for large-scale SID mission and decreased to within 20 ms for the real-time mission parameter.

eess.SY↗

arXiv2021

Comparison between Time Shifting Deviation and Cross-correlation Methods

Time delay estimation (TDE) is an important step to identify and locate vibration source. The TDE result can be obtained by cross-correlation method through seeking the maximum correlation peak of two signals. However, the cross-correlation method will induce random error when dealing with the nonstationary signal. We propose a novel time shifting deviation (TSDEV) method to solve this problem, which has been proved to achieve ultrahigh precision localization result in the fiber vibration monitoring system. This paper compares TSDEV method with cross-correlation in detail by simulating TDE process in different conditions, such as signals with arbitrary intercepted length, nonstationary drift and correlated noise. Besides, experimental demonstration has been carried out on 60 km fiber to localize a wide band vibration signal. The typical localization error is 2 m with standard deviation of 21.4 m using TSDEV method. It stands in clear contrast to the result of cross-correlation method, whose localization error is 70 m and the standard deviation is 208.4 m. Compared with cross-correlation method, TSDEV has the same resistance to white noise, but has fewer boundary conditions and better suppression on linear drift or common noise, which leads to more precise TDE results.

eess.SP↗

arXiv2021

A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization

Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance in edge computing, we introduce a low-power Multi-layer Perceptron (MLP) accelerator based on a pipelined matrix multiplication scheme and a nonuniform quantization methodology. The implementation is running on Field-programmable Gate Array (FPGA) devices and tested its performance on handwritten digit classification and Q-learning tasks. Results show that our method can achieve better performance with fewer power consumption.

cs.LG↗

arXiv2021

Graph2Graph Learning with Conditional Autoregressive Models

We present a graph neural network model for solving graph-to-graph learning problems. Most deep learning on graphs considers ``simple'' problems such as graph classification or regressing real-valued graph properties. For such tasks, the main requirement for intermediate representations of the data is to maintain the structure needed for output, i.e., keeping classes separated or maintaining the order indicated by the regressor. However, a number of learning tasks, such as regressing graph-valued output, generative models, or graph autoencoders, aim to predict a graph-structured output. In order to successfully do this, the learned representations need to preserve far more structure. We present a conditional auto-regressive model for graph-to-graph learning and illustrate its representational capabilities via experiments on challenging subgraph predictions from graph algorithmics; as a graph autoencoder for reconstruction and visualization; and on pretraining representations that allow graph classification with limited labeled data.

cs.LG↗

arXiv2021

Truncation-Free Matching System for Display Advertising at Alibaba

Matching module plays a critical role in display advertising systems. Without query from user, it is challenging for system to match user traffic and ads suitably. System packs up a group of users with common properties such as the same gender or similar shopping interests into a crowd. Here term crowd can be viewed as a tag over users. Then advertisers bid for different crowds and deliver their ads to those targeted users. Matching module in most industrial display advertising systems follows a two-stage paradigm. When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds. However, in applications such as display advertising at Alibaba, with very large volumes of crowds and ads, both stages of matching have to truncate the long-tailed parts for online serving, under limited latency. That's to say, not all ads have the chance to participate in online matching. This results in sub-optimal result for both advertising performance and platform revenue. In this paper, we study the truncation problem and propose a Truncation Free Matching System (TFMS). The basic idea is to decouple the matching computation from the online pipeline. Instead of executing the two-stage matching when user visits, TFMS utilizes a near-line truncation-free matching to pre-calculate and store those top valuable ads for each user. Then the online pipeline just needs to fetch the pre-stored ads as matching results. In this way, we can jump out of online system's latency and computation cost limitations, and leverage flexible computation resource to finish the user-ad matching. TFMS has been deployed in our productive system since 2019, bringing (i) more than 50% improvement of impressions for advertisers who encountered truncation before, (ii) 9.4% Revenue Per Mile gain, which is significant enough for the business.

cs.IR↗