arXiv subjects

Rong Zhou

Publications and source records attributed to Rong Zhou.

At least 55 records · Page 3Linked to original sources

arXiv2023

Anisotropic weighted isoperimetric inequalities for star-shaped and $F$-mean convex hypersurface

We prove two anisotropic type weighted geometric inequalities that hold for star-shaped and $F$-mean convex hypersurfaces in $\mathbb{R}^{n+1}$. These inequalities involve the anisotropic $p$-momentum, the anisotropic perimeter and the volume of the region enclosed by the hypersurface. We show that the Wulff shape of $F$ is the unique minimizer of the corresponding functionals among all star-shaped and $F$-mean convex sets. We also consider their quantitative versions characterized by the Hausdorff distance between the hypersurface and a rescaled Wulff shape. As a corollary, we obtain the stability of the Weinstock inequality for star-shaped and strictly mean convex domains, which requires weaker convexity compared to \cite{Gavitone}.

math.DG↗

arXiv2023

Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V

In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i.e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task. Our experiments thoroughly assess GPT-4V's proficiency in answering questions paired with images using both pathology and radiology datasets from 11 modalities (e.g. Microscopy, Dermoscopy, X-ray, CT, etc.) and fifteen objects of interests (brain, liver, lung, etc.). Our datasets encompass a comprehensive range of medical inquiries, including sixteen distinct question types. Throughout our evaluations, we devised textual prompts for GPT-4V, directing it to synergize visual and textual information. The experiments with accuracy score conclude that the current version of GPT-4V is not recommended for real-world diagnostics due to its unreliable and suboptimal accuracy in responding to diagnostic medical questions. In addition, we delineate seven unique facets of GPT-4V's behavior in medical VQA, highlighting its constraints within this complex arena. The complete details of our evaluation cases are accessible at https://github.com/ZhilingYan/GPT4V-Medical-Report.

cs.CV↗

arXiv2023

Learning Apparent Diffusion Coefficient Maps from Accelerated Radial k-Space Diffusion-Weighted MRI in Mice using a Deep CNN-Transformer Model

Purpose: To accelerate radially sampled diffusion weighted spin-echo (Rad-DW-SE) acquisition method for generating high quality apparent diffusion coefficient (ADC) maps. Methods: A deep learning method was developed to generate accurate ADC maps from accelerated DWI data acquired with the Rad-DW-SE method. The deep learning method integrates convolutional neural networks (CNNs) with vision transformers to generate high quality ADC maps from accelerated DWI data, regularized by a monoexponential ADC model fitting term. A model was trained on DWI data of 147 mice and evaluated on DWI data of 36 mice, with acceleration factors of 4x and 8x compared to the original acquisition parameters. We have made our code publicly available at GitHub: https://github.com/ymli39/DeepADC-Net-Learning-Apparent-Diffusion-Coefficient-Maps, and our dataset can be downloaded at https://pennpancreaticcancerimagingresource.github.io/data.html. Results: Ablation studies and experimental results have demonstrated that the proposed deep learning model generates higher quality ADC maps from accelerated DWI data than alternative deep learning methods under comparison when their performance is quantified in whole images as well as in regions of interest, including tumors, kidneys, and muscles. Conclusions: The deep learning method with integrated CNNs and transformers provides an effective means to accurately compute ADC maps from accelerated DWI data acquired with the Rad-DW-SE method.

eess.IV↗

arXiv2023

Stability of Alexandrov-Fenchel Type Inequalities for Nearly Spherical Sets in Space Forms

In this paper, we first derive a quantitative quermassintegral inequality for nearly spherical sets in $\mathbb{H}^{n+1}$ and $\mathbb{S}^{n+1}$, which is a generalization of the quantitative Alexandrov-Fenchel inequality proved in $\mathbb{R}^{n+1}$ [22]. Then we use this method to derive the stability of some geometric inequalities involving weighted curvature integrals and quermassintegrals for nearly spherical sets in $\mathbb{R}^{n+1}$ and $\mathbb{H}^{n+1}$.

math.DG↗

arXiv2023

GRB 220408B: A Three-Episode Burst from a Precessing Jet

Jet precession has previously been proposed to explain the apparently repeating features in the light curves of a few gamma-ray bursts (GRBs). In this {\it Letter}, we further apply the precession model to a bright GRB 220408B by examining both its temporal and spectral consistency with the predictions of the model. As one of the recently confirmed GRBs observed by our GRID CubeSat mission, GRB 220408B is noteworthy as it exhibits three apparently similar emission episodes. Furthermore, the similarities are reinforced by their strong temporal correlations and similar features in terms of spectral evolution and spectral lags. Our analysis demonstrates that these features can be well explained by the modulated emission of a Fast-Rise-Exponential-Decay (FRED) shape light curve intrinsically produced by a precessing jet with a precession period of $18.4 \pm 0.2$ seconds, a nutation period of $11.1 \pm 0.2$ seconds and viewed off-axis. This study provides a straightforward explanation for the complex yet similar multi-episode GRB light curves.

astro-ph.HE↗

arXiv2022

Normative Modeling via Conditional Variational Autoencoder and Adversarial Learning to Identify Brain Dysfunction in Alzheimer's Disease

Normative modeling is an emerging and promising approach to effectively study disorder heterogeneity in individual participants. In this study, we propose a novel normative modeling method by combining conditional variational autoencoder with adversarial learning (ACVAE) to identify brain dysfunction in Alzheimer's Disease (AD). Specifically, we first train a conditional VAE on the healthy control (HC) group to create a normative model conditioned on covariates like age, gender and intracranial volume. Then we incorporate an adversarial training process to construct a discriminative feature space that can better generalize to unseen data. Finally, we compute deviations from the normal criterion at the patient level to determine which brain regions were associated with AD. Our experiments on OASIS-3 database show that the deviation maps generated by our model exhibit higher sensitivity to AD compared to other deep normative models, and are able to better identify differences between the AD and HC groups.

cs.LG↗

arXiv2021

Stabilizers of irreducible components of affine Deligne--Lusztig varieties

We study the $J_b(F)$-action on the set of top-dimensional irreducible components of affine Deligne--Lusztig varieties in the affine Grassmannian. We show that the stabilizer of any such component is a parahoric subgroup of $J_b(F)$ of maximal volume, verifying a conjecture of X.~Zhu. As an application, we give a description of the set of top-dimensional irreducible components in the basic locus of Shimura varieties.

math.AG↗

arXiv2020

AutoADR: Automatic Model Design for Ad Relevance

Large-scale pre-trained models have attracted extensive attention in the research community and shown promising results on various tasks of natural language processing. However, these pre-trained models are memory and computation intensive, hindering their deployment into industrial online systems like Ad Relevance. Meanwhile, how to design an effective yet efficient model architecture is another challenging problem in online Ad Relevance. Recently, AutoML shed new lights on architecture design, but how to integrate it with pre-trained language models remains unsettled. In this paper, we propose AutoADR (Automatic model design for AD Relevance) -- a novel end-to-end framework to address this challenge, and share our experience to ship these cutting-edge techniques into online Ad Relevance system at Microsoft Bing. Specifically, AutoADR leverages a one-shot neural architecture search algorithm to find a tailored network architecture for Ad Relevance. The search process is simultaneously guided by knowledge distillation from a large pre-trained teacher model (e.g. BERT), while taking the online serving constraints (e.g. memory and latency) into consideration. We add the model designed by AutoADR as a sub-model into the production Ad Relevance model. This additional sub-model improves the Precision-Recall AUC (PR AUC) on top of the original Ad Relevance model by 2.65X of the normalized shipping bar. More importantly, adding this automatically designed sub-model leads to a statistically significant 4.6% Bad-Ad ratio reduction in online A/B testing. This model has been shipped into Microsoft Bing Ad Relevance Production model.

cs.CL↗

arXiv2020

Serre-Tate theory for Shimura varieties of Hodge type

We study the formal neighbourhood of a point in $μ$-ordinary locus of an integral model of a Hodge type Shimura variety. We show that this formal neighbourhood has a structure of a shifted cascade. Moreover we show that the CM points on the formal neighbourhood are dense and that the identity section of the shifted cascade corresponds to a lift of the abelian variety which has a characterization in terms of its endomorphisms in analogy with the Serre-Tate canonical lift of an ordinary abelian variety.

math.NT↗

arXiv2020

Twisted orbital integrals and irreducible components of affine Deligne-Lusztig varieties

We analyze the asymptotic behavior of certain twisted orbital integrals arising from the study of affine Deligne-Lusztig varieties. The main tools include the Base Change Fundamental Lemma and $q$-analogues of the Kostant partition functions. As an application we prove a conjecture of Miaofen Chen and Xinwen Zhu, relating the set of irreducible components of an affine Deligne-Lusztig variety modulo the action of the $σ$-centralizer group to the Mirkovic-Vilonen basis of a certain weight space of a representation of the Langlands dual group.

math.NT↗

arXiv2019

Motivic cohomology of quaternionic Shimura varieties and level raising

We study the motivic cohomology of the special fiber of quaternionic Shimura varieties at a prime of good reduction. We exhibit classes in these motivic cohomology groups and use this to give an explicit geometric realization of level raising between Hilbert modular forms. The main ingredient for our construction is a form of Ihara's Lemma for compact quaternionic Shimura surfaces which we prove by generalizing a method of Diamond-Taylor. Along the way we also verify the Hecke orbit conjecture for these quaternionic Shimura varieties which is a key input for our proof of Ihara's Lemma.

math.NT↗

arXiv2018

Learning Role-based Graph Embeddings

Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes (if available). This is achieved by learning functions that generalize to new nodes and graphs. We show that our proposed framework is effective with an average AUC improvement of 16.55% while requiring on average 853x less space than existing methods on a variety of graphs.

stat.ML↗

arXiv2018

Mod-$p$ isogeny classes on Shimura varieties with parahoric level structure

We study the special fiber of the integral models for Shimura varieties of Hodge type with parahoric level structure constructed by Kisin and Pappas in [KP]. We show that when the group is residually split, the points in the mod $p$ isogeny classes have the form predicted by the Langlands Rapoport conjecture in [LR]. We also verify most of the He-Rapoport axioms for these integral models without the residually split assumption. This allows us to prove that all Newton strata are non-empty for these models.

math.NT↗

arXiv2017

Inductive Representation Learning in Large Attributed Graphs

Graphs (networks) are ubiquitous and allow us to model entities (nodes) and the dependencies (edges) between them. Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as classification, anomaly detection, link prediction, among many others. Many existing techniques use random walks as a basis for learning features or estimating the parameters of a graph model for a downstream prediction task. Examples include recent node embedding methods such as DeepWalk, node2vec, as well as graph-based deep learning algorithms. However, the simple random walk used by these methods is fundamentally tied to the identity of the node. This has three main disadvantages. First, these approaches are inherently transductive and do not generalize to unseen nodes and other graphs. Second, they are not space-efficient as a feature vector is learned for each node which is impractical for large graphs. Third, most of these approaches lack support for attributed graphs. To make these methods more generally applicable, we propose a framework for inductive network representation learning based on the notion of attributed random walk that is not tied to node identity and is instead based on learning a function $Φ: \mathrm{\rm \bf x} \rightarrow w$ that maps a node attribute vector $\mathrm{\rm \bf x}$ to a type $w$. This framework serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many other previous methods that leverage traditional random walks.

stat.ML↗

arXiv2017

Similarity-based Multi-label Learning

Multi-label classification is an important learning problem with many applications. In this work, we propose a principled similarity-based approach for multi-label learning called SML. We also introduce a similarity-based approach for predicting the label set size. The experimental results demonstrate the effectiveness of SML for multi-label classification where it is shown to compare favorably with a wide variety of existing algorithms across a range of evaluation criterion.

stat.ML↗

arXiv2017

Deep Feature Learning for Graphs

This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the output from the previous layer to learn features of a higher-order. Contrary to previous work, DeepGL learns relational functions (each representing a feature) that generalize across-networks and therefore useful for graph-based transfer learning tasks. Moreover, DeepGL naturally supports attributed graphs, learns interpretable features, and is space-efficient (by learning sparse feature vectors). In addition, DeepGL is expressive, flexible with many interchangeable components, efficient with a time complexity of $\mathcal{O}(|E|)$, and scalable for large networks via an efficient parallel implementation. Compared with the state-of-the-art method, DeepGL is (1) effective for across-network transfer learning tasks and attributed graph representation learning, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 182x speedup in runtime performance, and (4) accurate with an average improvement of 20% or more on many learning tasks.

stat.ML↗

arXiv2017

A Framework for Generalizing Graph-based Representation Learning Methods

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to node identity. In this work, we introduce the notion of attributed random walks which serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes (if available). This is achieved by learning functions that generalize to new nodes and graphs. We show that our proposed framework is effective with an average AUC improvement of 16.1% while requiring on average 853 times less space than existing methods on a variety of graphs from several domains.

stat.ML↗

arXiv2017

Estimation of Graphlet Statistics

Graphlets are induced subgraphs of a large network and are important for understanding and modeling complex networks. Despite their practical importance, graphlets have been severely limited to applications and domains with relatively small graphs. Most previous work has focused on exact algorithms, however, it is often too expensive to compute graphlets exactly in massive networks with billions of edges, and finding an approximate count is usually sufficient for many applications. In this work, we propose an unbiased graphlet estimation framework that is (a) fast with significant speedups compared to the state-of-the-art, (b) parallel with nearly linear-speedups, (c) accurate with <1% relative error, (d) scalable and space-efficient for massive networks with billions of edges, and (e) flexible for a variety of real-world settings, as well as estimating macro and micro-level graphlet statistics (e.g., counts) of both connected and disconnected graphlets. In addition, an adaptive approach is introduced that finds the smallest sample size required to obtain estimates within a given user-defined error bound. On 300 networks from 20 domains, we obtain <1% relative error for all graphlets. This is significantly more accurate than existing methods while using less data. Moreover, it takes a few seconds on billion edge graphs (as opposed to days/weeks). These are by far the largest graphlet computations to date.

cs.SI↗