arXiv subjects

Yao Zhang

Publications and source records attributed to Yao Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2023

Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease

Objective: Bleeding from gastroesophageal varices (GEV) is a medical emergency associated with high mortality. We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography (2D-SWE) of the liver and spleen to precisely assess the risk of GEV and high-risk gastroesophageal varices (HRV). Design: A prospective multicenter study was conducted in patients with compensated advanced chronic liver disease. 305 patients were enrolled from 12 hospitals, and finally 265 patients were included, with 1136 liver stiffness measurement (LSM) images and 1042 spleen stiffness measurement (SSM) images generated by 2D-SWE. We leveraged deep learning methods to uncover associations between image features and patient risk, and thus conducted models to predict GEV and HRV. Results: A multi-modality Deep Learning Risk Prediction model (DLRP) was constructed to assess GEV and HRV, based on LSM and SSM images, and clinical information. Validation analysis revealed that the AUCs of DLRP were 0.91 for GEV (95% CI 0.90 to 0.93, p < 0.05) and 0.88 for HRV (95% CI 0.86 to 0.89, p < 0.01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM. Moreover, DLPR was better than the model using individual parameters, including LSM and SSM images. In HRV prediction, the 2D-SWE images of SSM outperform LSM (p < 0.01). Conclusion: DLRP shows excellent performance in predicting GEV and HRV over canonical risk indicators LSM and SSM. Additionally, the 2D-SWE images of SSM provided more information for better accuracy in predicting HRV than the LSM.

q-bio.TO↗

arXiv2023

Incentive-Compatible Selection for One or Two Influentials

Selecting influentials in networks against strategic manipulations has attracted many researchers' attention and it also has many practical applications. Here, we aim to select one or two influentials in terms of progeny (the influential power) and prevent agents from manipulating their edges (incentive compatibility). The existing studies mostly focused on selecting a single influential for this setting. Zhang et al. [2021] studied the problem of selecting one agent and proved an upper bound of 1/(1+ln2) to approximate the optimal selection. In this paper, we first design a mechanism to actually reach the bound. Then, we move this forward to choosing two agents and propose a mechanism to achieve an approximation ratio of (3+ln2)/(4(1+ln2)) (approx. 0.54).

cs.GT↗

arXiv2023

ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations

Since conventional knowledge embedding models cannot take full advantage of the abundant textual information, there have been extensive research efforts in enhancing knowledge embedding using texts. However, existing enhancement approaches cannot apply to temporal knowledge graphs (tKGs), which contain time-dependent event knowledge with complex temporal dynamics. Specifically, existing enhancement approaches often assume knowledge embedding is time-independent. In contrast, the entity embedding in tKG models usually evolves, which poses the challenge of aligning temporally relevant texts with entities. To this end, we propose to study enhancing temporal knowledge embedding with textual data in this paper. As an approach to this task, we propose Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations (ECOLA), which takes the temporal aspect into account and injects textual information into temporal knowledge embedding. To evaluate ECOLA, we introduce three new datasets for training and evaluating ECOLA. Extensive experiments show that ECOLA significantly enhances temporal KG embedding models with up to 287% relative improvements regarding Hits@1 on the link prediction task. The code and models are publicly available on https://anonymous.4open.science/r/ECOLA.

cs.CL↗

arXiv2023

High speed free-space optical communication using standard fiber communication component without optical amplification

Free-space optical communication (FSO) can achieve fast, secure and license-free communication without need for physical cables, making it a cost-effective, energy-efficient and flexible solution when the fiber connection is unavailable. To establish FSO connection on-demand, it is essential to build portable FSO devices with compact structure and light weight. Here, we develop a miniaturized FSO system and realize 9.16 Gbps FSO between two nodes that is 1 km apart, using a commercial single-mode-fiber-coupled optical transceiver module without optical amplification. Using our 4-stage acquisition, pointing and tracking (APT) systems, the tracking error is within 3 μrad and results an average link loss of 13.7 dB, which is the key for this high-bandwidth FSO demonstration without optical amplification. Our FSO link has been tested up to 4 km, with link loss of 18 dB that is limited by the foggy weather during the test. Longer FSO distances can be expected with better weather condition and optical amplification. With single FSO device weight of only 9.5 kg, this result arouses massive applications of field-deployable high-speed wireless communication.

eess.SP↗

arXiv2023

What is a randomization test?

The meaning of randomization tests has become obscure in statistics education and practice over the last century. This article makes a fresh attempt at rectifying this core concept of statistics. A new term -- "quasi-randomization test" -- is introduced to define significance tests based on theoretical models and distinguish these tests from the "randomization tests" based on the physical act of randomization. The practical importance of this distinction is illustrated through a real stepped-wedge cluster-randomized trial. Building on the recent literature of randomization inference, a general framework of conditional randomization tests is developed and some practical methods to construct conditioning events are given. The proposed terminology and framework are then applied to understand several widely used (quasi-)randomization tests, including Fisher's exact test, permutation tests for treatment effect, quasi-randomization tests for independence and conditional independence, adaptive randomization, and conformal prediction.

stat.ME↗

arXiv2023

Chinese Intermediate English Learners outdid ChatGPT in deep cohesion: Evidence from English narrative writing

ChatGPT is a publicly available chatbot that can quickly generate texts on given topics, but it is unknown whether the chatbot is really superior to human writers in all aspects of writing and whether its writing quality can be prominently improved on the basis of updating commands. Consequently, this study compared the writing performance on a narrative topic by ChatGPT and Chinese intermediate English (CIE) learners so as to reveal the chatbot's advantage and disadvantage in writing. The data were analyzed in terms of five discourse components using Coh-Metrix (a special instrument for analyzing language discourses), and the results revealed that ChatGPT performed better than human writers in narrativity, word concreteness, and referential cohesion, but worse in syntactic simplicity and deep cohesion in its initial version. After more revision commands were updated, while the resulting version was facilitated in syntactic simplicity, yet it is still lagged far behind CIE learners' writing in deep cohesion. In addition, the correlation analysis of the discourse components suggests that narrativity was correlated with referential cohesion in both ChatGPT and human writers, but the correlations varied within each group.

cs.CL↗

arXiv2023

SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency

Recently, the dominant DETR-based approaches apply central-concept spatial prior to accelerate Transformer detector convergency. These methods gradually refine the reference points to the center of target objects and imbue object queries with the updated central reference information for spatially conditional attention. However, centralizing reference points may severely deteriorate queries' saliency and confuse detectors due to the indiscriminative spatial prior. To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (SAP-DETR) by treating object detection as a transformation from salient points to instance objects. In SAP-DETR, we explicitly initialize a query-specific reference point for each object query, gradually aggregate them into an instance object, and then predict the distance from each side of the bounding box to these points. By rapidly attending to query-specific reference region and other conditional extreme regions from the image features, SAP-DETR can effectively bridge the gap between the salient point and the query-based Transformer detector with a significant convergency speed. Our extensive experiments have demonstrated that SAP-DETR achieves 1.4 times convergency speed with competitive performance. Under the standard training scheme, SAP-DETR stably promotes the SOTA approaches by 1.0 AP. Based on ResNet-DC-101, SAP-DETR achieves 46.9 AP.

cs.CV↗

arXiv2023

A Redistribution Framework for Diffusion Auctions

Redistribution mechanism design aims to redistribute the revenue collected by a truthful auction back to its participants without affecting the truthfulness. We study redistribution mechanisms for diffusion auctions, which is a new trend in mechanism design [19]. The key property of a diffusion auction is that the existing participants are incentivized to invite new participants to join the auctions. Hence, when we design redistributions, we also need to maintain this incentive. Existing redistribution mechanisms in the traditional setting are targeted at modifying the payment design of a truthful mechanism, such as the Vickrey auction. In this paper, we do not focus on one specific mechanism. Instead, we propose a general framework to redistribute the revenue back for all truthful diffusion auctions for selling a single item. The framework treats the original truthful diffusion auction as a black box, and it does not affect its truthfulness. The framework can also distribute back almost all the revenue.

cs.GT↗

arXiv2023

Distributed Mechanism Design in Social Networks

Designing auctions to incentivize buyers to invite new buyers via their social connections is a new trend in mechanism design. The challenge is that buyers are competitors and we need to design proper incentives for them to invite each other. For selling a single item, many interesting mechanisms have been proposed. However, all the mechanisms require the seller or a third party to be trustworthy to execute the mechanisms. In addition, the owner of the mechanism will know all the connections of the network after the execution, which poses a potential privacy issue. Hence, distributed mechanisms to avoid the privacy issue are more appealing in practice. Therefore, in this paper, we propose the first distributed mechanism in social networks without revealing buyers' private connections to anyone, and it achieves complete decentralization that does not rely on any trustworthy third party. Moreover, the centralized reduction of our mechanism also offers a novel way to compute players' contributions compared to the existing solutions.

cs.GT↗

arXiv2023

Ultrafast Plasmon-mediated Superradiance from Vertically Standing Molecules in Metallic Nanocavities

Plasmon-mediated superradiance for molecules around metallic nanospheres was proposed ten years ago. However, its demonstration has not been achieved yet due to the experimental difficulty of positioning molecules, and the theoretical limitation to the enhanced collective rate of low excited molecules. In this Letter, we propose that the ultrafast plasmon-mediated superradiant pulses can be observed with strongly excited methylene blue molecules standing vertically inside gold nanoparticle-on-mirror nanocavities. Our simulations indicate that in this system the molecules could interact with each other via plasmon- and free-space mediated coherent and dissipative coupling. More importantly, the coherent coupling mediated by short-ranged propagating surface plasmons cancel largely the direct dipole-dipole coupling mediated by the free-space field, and the dominated dissipative coupling mediated by relatively long-ranged gap plasmons enables the ultrafast superradiant pulses within picosecond scale. Our study opens up the possibility of studying the rich superradiant effects from the quantum emitters in a sub-wavelength volumn by engineering the plasmonic environments.

quant-ph↗

arXiv2023

TIGER: Temporal Interaction Graph Embedding with Restarts

Temporal interaction graphs (TIGs), consisting of sequences of timestamped interaction events, are prevalent in fields like e-commerce and social networks. To better learn dynamic node embeddings that vary over time, researchers have proposed a series of temporal graph neural networks for TIGs. However, due to the entangled temporal and structural dependencies, existing methods have to process the sequence of events chronologically and consecutively to ensure node representations are up-to-date. This prevents existing models from parallelization and reduces their flexibility in industrial applications. To tackle the above challenge, in this paper, we propose TIGER, a TIG embedding model that can restart at any timestamp. We introduce a restarter module that generates surrogate representations acting as the warm initialization of node representations. By restarting from multiple timestamps simultaneously, we divide the sequence into multiple chunks and naturally enable the parallelization of the model. Moreover, in contrast to previous models that utilize a single memory unit, we introduce a dual memory module to better exploit neighborhood information and alleviate the staleness problem. Extensive experiments on four public datasets and one industrial dataset are conducted, and the results verify both the effectiveness and the efficiency of our work.

cs.LG↗

arXiv2023

ConsRec: Learning Consensus Behind Interactions for Group Recommendation

Since group activities have become very common in daily life, there is an urgent demand for generating recommendations for a group of users, referred to as group recommendation task. Existing group recommendation methods usually infer groups' preferences via aggregating diverse members' interests. Actually, groups' ultimate choice involves compromises between members, and finally, an agreement can be reached. However, existing individual information aggregation lacks a holistic group-level consideration, failing to capture the consensus information. Besides, their specific aggregation strategies either suffer from high computational costs or become too coarse-grained to make precise predictions. To solve the aforementioned limitations, in this paper, we focus on exploring consensus behind group behavior data. To comprehensively capture the group consensus, we innovatively design three distinct views which provide mutually complementary information to enable multi-view learning, including member-level aggregation, item-level tastes, and group-level inherent preferences. To integrate and balance the multi-view information, an adaptive fusion component is further proposed. As to member-level aggregation, different from existing linear or attentive strategies, we design a novel hypergraph neural network that allows for efficient hypergraph convolutional operations to generate expressive member-level aggregation. We evaluate our ConsRec on two real-world datasets and experimental results show that our model outperforms state-of-the-art methods. An extensive case study also verifies the effectiveness of consensus modeling.

cs.IR↗

arXiv2022

A Survey of Visual Transformers

Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP). Inspired by such significant achievements, some pioneering works have recently been done on employing Transformer-liked architectures in the computer vision (CV) field, which have demonstrated their effectiveness on three fundamental CV tasks (classification, detection, and segmentation) as well as multiple sensory data stream (images, point clouds, and vision-language data). Because of their competitive modeling capabilities, the visual Transformers have achieved impressive performance improvements over multiple benchmarks as compared with modern Convolution Neural Networks (CNNs). In this survey, we have reviewed over one hundred of different visual Transformers comprehensively according to three fundamental CV tasks and different data stream types, where a taxonomy is proposed to organize the representative methods according to their motivations, structures, and application scenarios. Because of their differences on training settings and dedicated vision tasks, we have also evaluated and compared all these existing visual Transformers under different configurations. Furthermore, we have revealed a series of essential but unexploited aspects that may empower such visual Transformers to stand out from numerous architectures, e.g., slack high-level semantic embeddings to bridge the gap between the visual Transformers and the sequential ones. Finally, three promising research directions are suggested for future investment. We will continue to update the latest articles and their released source codes at https://github.com/liuyang-ict/awesome-visual-transformers.

cs.CV↗

arXiv2022

CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering

Visual Question Answering (VQA) is a multi-discipline research task. To produce the right answer, it requires an understanding of the visual content of images, the natural language questions, as well as commonsense reasoning over the information contained in the image and world knowledge. Recently, large-scale Vision-and-Language Pre-trained Models (VLPMs) have been the mainstream approach to VQA tasks due to their superior performance. The standard practice is to fine-tune large-scale VLPMs pre-trained on huge general-domain datasets using the domain-specific VQA datasets. However, in reality, the application domain can change over time, necessitating VLPMs to continually learn and adapt to new domains without forgetting previously acquired knowledge. Most existing continual learning (CL) research concentrates on unimodal tasks, whereas a more practical application scenario, i.e, CL on cross-domain VQA, has not been studied. Motivated by this, we introduce CL-CrossVQA, a rigorous Continual Learning benchmark for Cross-domain Visual Question Answering, through which we conduct extensive experiments on 4 VLPMs, 4 CL approaches, and 5 VQA datasets from different domains. In addition, by probing the forgetting phenomenon of the intermediate layers, we provide insights into how model architecture affects CL performance, why CL approaches can help mitigate forgetting in VLPMs to some extent, and how to design CL approaches suitable for VLPMs in this challenging continual learning environment. To facilitate future work on CL for cross-domain VQA, we will release our datasets and code.

cs.CV↗

arXiv2022

Learning to Learn Domain-invariant Parameters for Domain Generalization

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains. Motivated by the insight that only partial parameters of DNNs are optimized to extract domain-invariant representations, we expect a general model that is capable of well perceiving and emphatically updating such domain-invariant parameters. In this paper, we propose two modules of Domain Decoupling and Combination (DDC) and Domain-invariance-guided Backpropagation (DIGB), which can encourage such general model to focus on the parameters that have a unified optimization direction between pairs of contrastive samples. Our extensive experiments on two benchmarks have demonstrated that our proposed method has achieved state-of-the-art performance with strong generalization capability.

cs.LG↗

arXiv2022

CLARE: A Semi-supervised Community Detection Algorithm

Community detection refers to the task of discovering closely related subgraphs to understand the networks. However, traditional community detection algorithms fail to pinpoint a particular kind of community. This limits its applicability in real-world networks, e.g., distinguishing fraud groups from normal ones in transaction networks. Recently, semi-supervised community detection emerges as a solution. It aims to seek other similar communities in the network with few labeled communities as training data. Existing works can be regarded as seed-based: locate seed nodes and then develop communities around seeds. However, these methods are quite sensitive to the quality of selected seeds since communities generated around a mis-detected seed may be irrelevant. Besides, they have individual issues, e.g., inflexibility and high computational overhead. To address these issues, we propose CLARE, which consists of two key components, Community Locator and Community Rewriter. Our idea is that we can locate potential communities and then refine them. Therefore, the community locator is proposed for quickly locating potential communities by seeking subgraphs that are similar to training ones in the network. To further adjust these located communities, we devise the community rewriter. Enhanced by deep reinforcement learning, it suggests intelligent decisions, such as adding or dropping nodes, to refine community structures flexibly. Extensive experiments verify both the effectiveness and efficiency of our work compared with prior state-of-the-art approaches on multiple real-world datasets.

cs.SI↗

arXiv2022

Optomechanical Effects in Nanocavity-enhanced Resonant Raman Scattering of a Single Molecule

In this article, we address the optomechanical effects in surface-enhanced resonant Raman scattering (SERRS) from a single molecule in a nano-particle on mirror (NPoM) nanocavity by developing a quantum master equation theory, which combines macroscopic quantum electrodynamics and electron-vibration interaction within the framework of open quantum system theory. We supplement the theory with electromagnetic simulations and time-dependent density functional theory calculations in order to study the SERRS of a methylene blue molecule in a realistic NPoM nanocavity. The simulations allow us not only to identify the conditions to achieve conventional optomechanical effects, such as vibrational pumping, non-linear scaling of Stokes and anti-Stokes scattering, but also to discovery distinct behaviors, such as the saturation of exciton population, the emergence of Mollow triplet side-bands, and higher-order Raman scattering. All in all, our study might guide further investigations of optomechanical effects in resonant Raman scattering.

physics.optics↗

arXiv2022

RuDi: Explaining Behavior Sequence Models by Automatic Statistics Generation and Rule Distillation

Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with sophisticated designs have achieved promising results, the black-box nature hinders their applications due to fairness, explainability, and compliance consideration. Rule-based systems are considered reliable in these sensitive scenarios. However, building a rule system is labor-intensive. Experts need to find informative statistics from user behavior sequences, design rules based on statistics and assign weights to each rule. In this paper, we bridge the gap between effective but black-box models and transparent rule models. We propose a two-stage method, RuDi, that distills the knowledge of black-box teacher models into rule-based student models. We design a Monte Carlo tree search-based statistics generation method that can provide a set of informative statistics in the first stage. Then statistics are composed into logical rules with our proposed neural logical networks by mimicking the outputs of teacher models. We evaluate RuDi on three real-world public datasets and an industrial dataset to demonstrate its effectiveness.

cs.LG↗