arXiv subjects

Yao Zhang

Publications and source records attributed to Yao Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2022

Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfer

Accurate segmentation of cardiac structures can assist doctors to diagnose diseases, and to improve treatment planning, which is highly demanded in the clinical practice. However, the shortage of annotation and the variance of the data among different vendors and medical centers restrict the performance of advanced deep learning methods. In this work, we present a fully automatic method to segment cardiac structures including the left (LV) and right ventricle (RV) blood pools, as well as for the left ventricular myocardium (MYO) in MRI volumes. Specifically, we design a semi-supervised learning method to leverage unlabelled MRI sequence timeframes by label propagation. Then we exploit style transfer to reduce the variance among different centers and vendors for more robust cardiac image segmentation. We evaluate our method in the M&Ms challenge 7 , ranking 2nd place among 14 competitive teams.

eess.IV↗

arXiv2022

mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation

Accurate brain tumor segmentation from Magnetic Resonance Imaging (MRI) is desirable to joint learning of multimodal images. However, in clinical practice, it is not always possible to acquire a complete set of MRIs, and the problem of missing modalities causes severe performance degradation in existing multimodal segmentation methods. In this work, we present the first attempt to exploit the Transformer for multimodal brain tumor segmentation that is robust to any combinatorial subset of available modalities. Concretely, we propose a novel multimodal Medical Transformer (mmFormer) for incomplete multimodal learning with three main components: the hybrid modality-specific encoders that bridge a convolutional encoder and an intra-modal Transformer for both local and global context modeling within each modality; an inter-modal Transformer to build and align the long-range correlations across modalities for modality-invariant features with global semantics corresponding to tumor region; a decoder that performs a progressive up-sampling and fusion with the modality-invariant features to generate robust segmentation. Besides, auxiliary regularizers are introduced in both encoder and decoder to further enhance the model's robustness to incomplete modalities. We conduct extensive experiments on the public BraTS $2018$ dataset for brain tumor segmentation. The results demonstrate that the proposed mmFormer outperforms the state-of-the-art methods for incomplete multimodal brain tumor segmentation on almost all subsets of incomplete modalities, especially by an average 19.07% improvement of Dice on tumor segmentation with only one available modality. The code is available at https://github.com/YaoZhang93/mmFormer.

eess.IV↗

arXiv2022

Probing the atomically diffuse interfaces in core-shell nanoparticles in three dimensions

Deciphering the three-dimensional atomic structure of solid-solid interfaces in core-shell nanomaterials is the key to understand their remarkable catalytical, optical and electronic properties. Here, we probe the three-dimensional atomic structures of palladium-platinum core-shell nanoparticles at the single-atom level using atomic resolution electron tomography. We successfully quantify the rich structural variety of core-shell nanoparticles including bond length, coordination number, local bond orientation order, grain boundary, and five-fold symmetry, all in 3D at atomic resolution. Instead of forming an atomically-sharp boundary, the core-shell interface is atomically diffuse with an average thickness of 4.2 A, irrespective of the particle's size, morphology, or crystallographic texture. The high concentration of Pd in the interface is highly related to the electric double layers of the Pd seeds. These results advance our understanding of core-shell structures at the fundamental level, providing potential strategies into nanomaterial manipulation and chemical property regulation.

cond-mat.mtrl-sci↗

arXiv2022

ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification

Whole slide image (WSI) classification often relies on deep weakly supervised multiple instance learning (MIL) methods to handle gigapixel resolution images and slide-level labels. Yet the decent performance of deep learning comes from harnessing massive datasets and diverse samples, urging the need for efficient training pipelines for scaling to large datasets and data augmentation techniques for diversifying samples. However, current MIL-based WSI classification pipelines are memory-expensive and computation-inefficient since they usually assemble tens of thousands of patches as bags for computation. On the other hand, despite their popularity in other tasks, data augmentations are unexplored for WSI MIL frameworks. To address them, we propose ReMix, a general and efficient framework for MIL based WSI classification. It comprises two steps: reduce and mix. First, it reduces the number of instances in WSI bags by substituting instances with instance prototypes, i.e., patch cluster centroids. Then, we propose a ``Mix-the-bag'' augmentation that contains four online, stochastic and flexible latent space augmentations. It brings diverse and reliable class-identity-preserving semantic changes in the latent space while enforcing semantic-perturbation invariance. We evaluate ReMix on two public datasets with two state-of-the-art MIL methods. In our experiments, consistent improvements in precision, accuracy, and recall have been achieved but with orders of magnitude reduced training time and memory consumption, demonstrating ReMix's effectiveness and efficiency. Code is available.

cs.CV↗

arXiv2022

Carbon loss from forest degradation exceeds that from deforestation in the Brazilian Amazon

Spatial-temporal dynamics of aboveground biomass (AGB) and forest area affect the carbon cycle, climate, and biodiversity in the Brazilian Amazon. Here we investigate inter-annual changes of AGB and forest area by analyzing satellite-based annual AGB and forest area datasets. We found the gross forest area loss was larger in 2019 than in 2015, possibly due to recent loosening of forest protection policies. However, net AGB loss was three times smaller in 2019 than in 2015. During 2010-2019, the Brazilian Amazon had a cumulative gross loss of 4.45 Pg C against a gross gain of 3.78 Pg C, resulting in net AGB loss of 0.67 Pg C. Forest degradation (73%) contributed three times more to the gross AGB loss than deforestation (27%), given that the areal extent of degradation exceeds deforestation. This indicates that forest degradation has become the largest process driving carbon loss and should become a higher policy priority.

physics.bio-ph↗

arXiv2022

Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images

Purpose: Automated liver tumor segmentation from Computed Tomography (CT) images is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate liver tumor segmentation remains challenging due to the large variability of tumor sizes and inhomogeneous texture. Recent advances based on Fully Convolutional Network (FCN) for medical image segmentation drew on the success of learning discriminative pyramid features. In this paper, we propose a Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low- and high-level features embedded in FCN to segment liver tumor. Methods: We first design a powerful Pyramid Feature Encoder (PFE) to extract multi-level features from input images. Then we decouple the characteristics of features concerning spatial dimension (i.e., height, width, depth) and semantic dimension (i.e., channel). On top of that, we present two types of attention modules, Spatial Correlation (SpaCor) and Semantic Correlation (SemCor) modules, to recursively measure the correlation of multi-level features. The former selectively emphasizes global semantic information in low-level features with the guidance of high-level ones. The latter adaptively enhance spatial details in high-level features with the guidance of low-level ones. Results: We evaluate the DPC-Net on MICCAI 2017 LiTS Liver Tumor Segmentation (LiTS) challenge dataset. Dice Similarity Coefficient (DSC) and Average Symmetric Surface Distance (ASSD) are employed for evaluation. The proposed method obtains a DSC of 76.4% and an ASSD of 0.838 mm for liver tumor segmentation, outperforming the state-of-the-art methods. It also achieves a competitive results with a DSC of 96.0% and an ASSD of 1.636 mm for liver segmentation.

cs.CV↗

arXiv2022

Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy

Proactive dialogue system is able to lead the conversation to a goal topic and has advantaged potential in bargain, persuasion and negotiation. Current corpus-based learning manner limits its practical application in real-world scenarios. To this end, we contribute to advance the study of the proactive dialogue policy to a more natural and challenging setting, i.e., interacting dynamically with users. Further, we call attention to the non-cooperative user behavior -- the user talks about off-path topics when he/she is not satisfied with the previous topics introduced by the agent. We argue that the targets of reaching the goal topic quickly and maintaining a high user satisfaction are not always converge, because the topics close to the goal and the topics user preferred may not be the same. Towards this issue, we propose a new solution named I-Pro that can learn Proactive policy in the Interactive setting. Specifically, we learn the trade-off via a learned goal weight, which consists of four factors (dialogue turn, goal completion difficulty, user satisfaction estimation, and cooperative degree). The experimental results demonstrate I-Pro significantly outperforms baselines in terms of effectiveness and interpretability.

cs.IR↗

arXiv2022

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension

Procedural Multimodal Documents (PMDs) organize textual instructions and corresponding images step by step. Comprehending PMDs and inducing their representations for the downstream reasoning tasks is designated as Procedural MultiModal Machine Comprehension (M3C). In this study, we approach Procedural M3C at a fine-grained level (compared with existing explorations at a document or sentence level), that is, entity. With delicate consideration, we model entity both in its temporal and cross-modal relation and propose a novel Temporal-Modal Entity Graph (TMEG). Specifically, graph structure is formulated to capture textual and visual entities and trace their temporal-modal evolution. In addition, a graph aggregation module is introduced to conduct graph encoding and reasoning. Comprehensive experiments across three Procedural M3C tasks are conducted on a traditional dataset RecipeQA and our new dataset CraftQA, which can better evaluate the generalization of TMEG.

cs.CL↗

arXiv2022

Snowmass2021 Whitepaper: Muonium to antimuonium conversion

The spontaneous muonium to antimuonium conversion is one of the interesting charged lepton flavor violation processes. It serves as a clear indication of new physics and plays an important role in constraining the parameter space beyond Standard Model. MACE is a proposed experiment to probe such a phenomenon and expected to enhance the sensitivity to the conversion probability by more than two orders of magnitude from the current best upper constraint obtained by the PSI experiment two decades ago. Recent developments in the theoretical and experimental aspects to search for such a rare process are summarized.

hep-ph↗

arXiv2022

Collaborative Driving: Learning- Aided Joint Topology Formulation and Beamforming

Currently, autonomous vehicles are able to drive more naturally based on the driving policies learned from millions of driving miles in real environments. However, to further improve the automation level of vehicles is a challenging task, especially in the case of multi-vehicle cooperation. In recent heated discussions of 6G, millimeter-wave (mmWave) and terahertz (THz) bands are deemed to play important roles in new radio communication architectures and algorithms. To enable reliable autonomous driving in 6G, in this paper, we envision collaborative autonomous driving, a new framework that jointly controls driving topology and formulate vehicular networks in the mmWave/THz bands. As a swarm intelligence system, the collaborative driving scheme goes beyond existing autonomous driving patterns based on single-vehicle intelligence in terms of safety and efficiency. With efficient data sharing, the proposed framework is able to achieve cooperative sensing and load balancing so that improve sensing efficiency with saved computational resources. To deal with the new challenges in the collaborative driving framework, we further illustrate two promising approaches for mmWave/THz-based vehicle-to-vehicle (V2V) communications. Finally, we discuss several potential open research problems for the proposed collaborative driving scheme.

eess.SP↗

arXiv2022

Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs

In the question answering(QA) task, multi-hop reasoning framework has been extensively studied in recent years to perform more efficient and interpretable answer reasoning on the Knowledge Graph(KG). However, multi-hop reasoning is inapplicable for answering n-ary fact questions due to its linear reasoning nature. We discover that there are two feasible improvements: 1) upgrade the basic reasoning unit from entity or relation to fact; and 2) upgrade the reasoning structure from chain to tree. Based on these, we propose a novel fact-tree reasoning framework, through transforming the question into a fact tree and performing iterative fact reasoning on it to predict the correct answer. Through a comprehensive evaluation on the n-ary fact KGQA dataset introduced by this work, we demonstrate that the proposed fact-tree reasoning framework has the desired advantage of high answer prediction accuracy. In addition, we also evaluate the fact-tree reasoning framework on two binary KGQA datasets and show that our approach also has a strong reasoning ability compared with several excellent baselines. This work has direct implications for exploring complex reasoning scenarios and provides a preliminary baseline approach.

cs.AI↗

arXiv2022

Triangle Graph Interest Network for Click-through Rate Prediction

Click-through rate prediction is a critical task in online advertising. Currently, many existing methods attempt to extract user potential interests from historical click behavior sequences. However, it is difficult to handle sparse user behaviors or broaden interest exploration. Recently, some researchers incorporate the item-item co-occurrence graph as an auxiliary. Due to the elusiveness of user interests, those works still fail to determine the real motivation of user click behaviors. Besides, those works are more biased towards popular or similar commodities. They lack an effective mechanism to break the diversity restrictions. In this paper, we point out two special properties of triangles in the item-item graphs for recommendation systems: Intra-triangle homophily and Inter-triangle heterophiy. Based on this, we propose a novel and effective framework named Triangle Graph Interest Network (TGIN). For each clicked item in user behavior sequences, we introduce the triangles in its neighborhood of the item-item graphs as a supplement. TGIN regards these triangles as the basic units of user interests, which provide the clues to capture the real motivation for a user clicking an item. We characterize every click behavior by aggregating the information of several interest units to alleviate the elusive motivation problem. The attention mechanism determines users' preference for different interest units. By selecting diverse and relative triangles, TGIN brings in novel and serendipitous items to expand exploration opportunities of user interests. Then, we aggregate the multi-level interests of historical behavior sequences to improve CTR prediction. Extensive experiments on both public and industrial datasets clearly verify the effectiveness of our framework.

cs.AI↗

arXiv2022

Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects

Conditional average treatment effects (CATEs) allow us to understand the effect heterogeneity across a large population of individuals. However, typical CATE learners assume all confounding variables are measured in order for the CATE to be identifiable. This requirement can be satisfied by collecting many variables, at the expense of increased sample complexity for estimating CATEs. To combat this, we propose an energy-based model (EBM) that learns a low-dimensional representation of the variables by employing a noise contrastive loss function. With our EBM we introduce a preprocessing step that alleviates the dimensionality curse for any existing learner developed for estimating CATEs. We prove that our EBM keeps the representations partially identifiable up to some universal constant, as well as having universal approximation capability. These properties enable the representations to converge and keep the CATE estimates consistent. Experiments demonstrate the convergence of the representations, as well as show that estimating CATEs on our representations performs better than on the variables or the representations obtained through other dimensionality reduction methods.

cs.LG↗

arXiv2022

Task Allocation on Networks with Execution Uncertainty

We study a single task allocation problem where each worker connects to some other workers to form a network and the task requester only connects to some of the workers. The goal is to design an allocation mechanism such that each worker is incentivized to invite her neighbours to join the allocation, although they are competing for the task. Moreover, the performance of each worker is uncertain, which is modelled as the quality level of her task execution. The literature has proposed solutions to tackle the uncertainty problem by paying them after verifying their execution. Here, we extend the problem to the network setting. The challenge is that the requester relies on the workers to invite each other to find the best worker, and the performance of each worker is also unknown to the task requester. In this paper, we propose a new mechanism to solve the two challenges at the same time. The mechanism guarantees that inviting more workers and reporting/performing according to her true ability is a dominant strategy for each worker. We believe that the new solution can be widely applied in the digital economy powered by social connections such as crowdsourcing and contests.

cs.GT↗

arXiv2021

Incentives to Invite Others to Form Larger Coalitions

We study a cooperative game setting where the grand coalition may change since the initial players can invite more players. We focus on monotone games, i.e., adding more players to the grand coalition is not harmful. We model the invitation relationship as a directed acyclic graph. Our goal is to design a reward distribution mechanism for this new cooperative game setting such that players are incentivized to invite new players. In this paper, we propose the weighted permission Shapley value (inspired by permission structure and the weighted Shapley value) to achieve the goal. Our solution offers the very first attempt to incentivize players to invite more players to form a larger coalition via their private invitations in cooperative settings.

cs.GT↗

arXiv2021

Learning Based Task Offloading in Digital Twin Empowered Internet of Vehicles

Mobile edge computing has become an effective and fundamental paradigm for futuristic autonomous vehicles to offload computing tasks. However, due to the high mobility of vehicles, the dynamics of the wireless conditions, and the uncertainty of the arrival computing tasks, it is difficult for a single vehicle to determine the optimal offloading strategy. In this paper, we propose a Digital Twin (DT) empowered task offloading framework for Internet of Vehicles. As a software agent residing in the cloud, a DT can obtain both global network information by using communications among DTs, and historical information of a vehicle by using the communications within the twin. The global network information and historical vehicular information can significantly facilitate the offloading. In specific, to preserve the precious computing resource at different levels for most appropriate computing tasks, we integrate a learning scheme based on the prediction of futuristic computing tasks in DT. Accordingly, we model the offloading scheduling process as a Markov Decision Process (MDP) to minimize the long-term cost in terms of a trade off between task latency, energy consumption, and renting cost of clouds. Simulation results demonstrate that our algorithm can effectively find the optimal offloading strategy, as well as achieve the fast convergence speed and high performance, compared with other existing approaches.

cs.NI↗

arXiv2021

Picocavity-controlled Sub-nanometer Resolved Single Molecule Non-linear Fluorescence

In this article, we address fluorescence of single molecule inside a plasmonic picocavity by proposing a semi-classical theory via combining the macroscopic quantum electrodynamics theory and the open quantum system theory. To gain insights into the experimental results [Nat. Photonics, 14, 693 (2020)], we have further equipped this theory with the classical electromagnetic simulation of the pico-cavity, formed by single atom decorated silver STM tip and a silver substrate, and the time-dependent density functional theory calculation of zinc phthalocyanine molecule. Our simulations not only reproduce the fluorescence spectrum as measured in the experiment, confirming the influence of extreme field confinement afforded by the picocavity, but also reveal Rabi oscillation dynamics and Mollow triplets spectrum for moderate laser excitation. Thus, our study highlights the possibility of coherently manipulating the molecular state and exploring non-linear optical phenomena with the plasmonic picocavity.

cond-mat.mes-hall↗

arXiv2021

Autonomous Vehicular Networks: Perspective and Open Issues

The vehicular ad hoc networks (VANETs) have been researched for over twenty years. Although being a fundamental communication approach for vehicles, the conventional VANETs are challenged by the newly emerged autonomous vehicles (AVs) which introduce new features and challenges on communications. In the meantime, with the recent advances of artificial intelligence and 5G cellular networks, how should the fundamental framework of VANET evolve to utilize the new technologies? In this article, we reconsider the problem of vehicle-to-vehicle communications when the network is composed of AVs. We discuss the features and specific demands of AVs and how the conventional VANETs should adapt to fit them.

cs.NI↗