arXiv subjects

Xinrui Zhang

Publications and source records attributed to Xinrui Zhang.

25 records · Page 2Linked to original sources

arXiv2024

Dual-Domain CLIP-Assisted Residual Optimization Perception Model for Metal Artifact Reduction

Metal artifacts in computed tomography (CT) imaging pose significant challenges to accurate clinical diagnosis. The presence of high-density metallic implants results in artifacts that deteriorate image quality, manifesting in the forms of streaking, blurring, or beam hardening effects, etc. Nowadays, various deep learning-based approaches, particularly generative models, have been proposed for metal artifact reduction (MAR). However, these methods have limited perception ability in the diverse morphologies of different metal implants with artifacts, which may generate spurious anatomical structures and exhibit inferior generalization capability. To address the issues, we leverage visual-language model (VLM) to identify these morphological features and introduce them into a dual-domain CLIP-assisted residual optimization perception model (DuDoCROP) for MAR. Specifically, a dual-domain CLIP (DuDoCLIP) is fine-tuned on the image domain and sinogram domain using contrastive learning to extract semantic descriptions from anatomical structures and metal artifacts. Subsequently, a diffusion model is guided by the embeddings of DuDoCLIP, thereby enabling the dual-domain prior generation. Additionally, we design prompt engineering for more precise image-text descriptions that can enhance the model's perception capability. Then, a downstream task is devised for the one-step residual optimization and integration of dual-domain priors, while incorporating raw data fidelity. Ultimately, a new perceptual indicator is proposed to validate the model's perception and generation performance. With the assistance of DuDoCLIP, our DuDoCROP exhibits at least 63.7% higher generalization capability compared to the baseline model. Numerical experiments demonstrate that the proposed method can generate more realistic image structures and outperform other SOTA approaches both qualitatively and quantitatively.

cs.CV↗

arXiv2024

Signed Graph Representation Learning: A Survey

With the prevalence of social media, the connectedness between people has been greatly enhanced. Real-world relations between users on social media are often not limited to expressing positive ties such as friendship, trust, and agreement, but they also reflect negative ties such as enmity, mistrust, and disagreement, which can be well modelled by signed graphs. Signed Graph Representation Learning (SGRL) is an effective approach to analyze the complex patterns in real-world signed graphs with the co-existence of positive and negative links. In recent years, SGRL has witnesses fruitful results. SGRL tries to allocate low-dimensional representations to nodes and edges which could preserve the graph structure, attribute and some collective properties, e.g., balance theory and status theory. To the best of knowledge, there is no survey paper about SGRL up to now. In this paper, we present a broad review of SGRL methods and discuss some future research directions.

cs.SI↗

arXiv2023

SGA: A Graph Augmentation Method for Signed Graph Neural Networks

Signed Graph Neural Networks (SGNNs) are vital for analyzing complex patterns in real-world signed graphs containing positive and negative links. However, three key challenges hinder current SGNN-based signed graph representation learning: sparsity in signed graphs leaves latent structures undiscovered, unbalanced triangles pose representation difficulties for SGNN models, and real-world signed graph datasets often lack supplementary information like node labels and features. These constraints limit the potential of SGNN-based representation learning. We address these issues with data augmentation techniques. Despite many graph data augmentation methods existing for unsigned graphs, none are tailored for signed graphs. Our paper introduces the novel Signed Graph Augmentation framework (SGA), comprising three main components. First, we employ the SGNN model to encode the signed graph, extracting latent structural information for candidate augmentation structures. Second, we evaluate these candidate samples (edges) and select the most beneficial ones for modifying the original training set. Third, we propose a novel augmentation perspective that assigns varying training difficulty to training samples, enabling the design of a new training strategy. Extensive experiments on six real-world datasets (Bitcoin-alpha, Bitcoin-otc, Epinions, Slashdot, Wiki-elec, and Wiki-RfA) demonstrate that SGA significantly improves performance across multiple benchmarks. Our method outperforms baselines by up to 22.2% in AUC for SGCN on Wiki-RfA, 33.3% in F1-binary, 48.8% in F1-micro, and 36.3% in F1-macro for GAT on Bitcoin-alpha in link sign prediction.

cs.LG↗

arXiv2022

Frontrunning Block Attack in PoA Clique: A Case Study

As a fundamental technology of decentralized finance (DeFi), blockchain's ability to maintain a distributed fair ledger is threatened by manipulation of block/transaction order. In this paper, we propose a frontrunning block attack against the Clique-based Proof of Authority (PoA) algorithms. Our attack can frontrun blocks from honest in-turn sealers by breaking the proper order of leader selection. By falsifying the priority parameters (both \textit{difficulty} and \textit{delay time}), a malicious out-of-turn sealer can always successfully occupy the leader position and produce advantageous blocks that may contain profitable transactions. As a typical instance, we apply our attack to a mature Clique-engined project, HPB (\$3,058,901, as of April 2022). Experimental results demonstrate the effectiveness and feasibility. Then, we further recommend fixes that make identity checks effective. Our investigation and suggestion have been submitted to its official team and got their approval. We believe this work can act as, at least, a warning case for Clique variants to avoid repeating these design mistakes.

cs.CR↗

arXiv2021

An Offline Delegatable Cryptocurrency System

Blockchain-based cryptocurrencies, facilitating the convenience of payment by providing a decentralized online solution, have not been widely adopted so far due to slow confirmation of transactions. Offline delegation offers an efficient way to exchange coins. However, in such an approach, the coins that have been delegated confront the risk of being spent twice since the delegator's behaviour cannot be restricted easily on account of the absence of effective supervision. Even if a third party can be regarded as a judge between the delegator and delegatee to secure transactions, she still faces the threat of being compromised or providing misleading assure. Moreover, the approach equipped with a third party contradicts the real intention of decentralized cryptocurrency systems. In this paper, we propose \textit{DelegaCoin}, an offline delegatable cryptocurrency system to mitigate such an issue. We exploit trusted execution environments (TEEs) as decentralized "virtual agents" to prevent malicious delegation. In DelegaCoin, an owner can delegate his coins through offline-transactions without interacting with the blockchain network. A formal model and analysis, prototype implementation, and further evaluation demonstrate that our scheme is provably secure and practically feasible.

cs.CR↗

arXiv2020

CLUE: A Chinese Language Understanding Evaluation Benchmark

The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and applications in natural language processing (NLP). The problem, however, is that most such benchmarks are limited to English, which has made it difficult to replicate many of the successes in English NLU for other languages. To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark. CLUE is an open-ended, community-driven project that brings together 9 tasks spanning several well-established single-sentence/sentence-pair classification tasks, as well as machine reading comprehension, all on original Chinese text. To establish results on these tasks, we report scores using an exhaustive set of current state-of-the-art pre-trained Chinese models (9 in total). We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on Chinese NLU. Our benchmark is released at https://www.CLUEbenchmarks.com

cs.CL↗

arXiv2019

Production of the exotic neutron-deficient isotopes near N, Z = 50 in multinucleon transfer reactions

The multinucleon transfer reaction in the collisions of $^{40}$Ca+$^{124}$Sn at $E_{\textrm{c.m.}}=128.5$ MeV is investigated by using the improved quantum molecular dynamics model. The measured angular distributions and isotopic distributions of the products are reproduced reasonably well by the calculations. The multinucleon transfer reactions of $^{40}$Ca+$^{112}$Sn, $^{58}$Ni+$^{112}$Sn, $^{106}$Cd+$^{112}$Sn, and $^{48}$Ca+$^{112}$Sn are also studied. It shows that the combinations of neutron-deficient projectile and target are advantageous to produce the exotic neutron-deficient nuclei near $N, Z$ = 50. The charged particles emission plays an important role at small impact parameters in the deexcitation processes of the system. The production cross sections of the exotic neutron-deficient nuclei in multinucleon transfer reactions are much larger than those measured in the fragmentation and fusion-evaporation reactions. Several new neutron-deficient nuclei can be produced in $^{106}$Cd+$^{112}$Sn reaction. The corresponding production cross sections for the new neutron-deficient nuclei, $^{101,102}$Sb, $^{103}$Te, and $^{106,107}$I, are 2.0 nb, 4.1 nb, 6.5 nb, 0.4 $μ$b and 1.0 $μ$b, respectively.

nucl-th↗