arXiv subjects

Xiaobin Tang

Publications and source records attributed to Xiaobin Tang.

6 recordsLinked to original sources

arXiv2024

Seeing the Invisible through Speckle Images

Scattering obscures information carried by wave by producing a speckle pattern, posing a common challenge across various fields, including microscopy and astronomy. Traditional methods for extracting information from speckles often rely on significant physical assumptions, complex devices, or intricate algorithms. Recently, machine learning has emerged as a scalable and widely adopted tool for interpreting speckle patterns. However, most current machine learning techniques depend heavily on supervised training with extensive labeled datasets, which is problematic when labels are unavailable. To address this, we propose a strategy based on unsupervised learning for speckle recognition and evaluation, enabling to capture high-level information, such as object classes, directly from speckles without labeled data. By deriving invariant features from speckles, this method allows for the classification of speckles and facilitates diverse applications in image sensing. We experimentally validated our strategy through two significant applications: a noninvasive glucose monitoring system capable of differentiating time-lapse glucose concentrations, and a high-throughput communication system utilizing multimode fibers in dynamic environments. The versatility of this method holds promise for a broad range of far-reaching applications, including biomedical diagnostics, quantum network decoupling, and remote sensing.

physics.optics↗

arXiv2024

General Intelligent Imaging and Uncertainty Quantification by Deterministic Diffusion Model

Computational imaging is crucial in many disciplines from autonomous driving to life sciences. However, traditional model-driven and iterative methods consume large computational power and lack scalability for imaging. Deep learning (DL) is effective in processing local-to-local patterns, but it struggles with handling universal global-to-local (nonlocal) patterns under current frameworks. To bridge this gap, we propose a novel DL framework that employs a progressive denoising strategy, named the deterministic diffusion model (DDM), to facilitate general computational imaging at a low cost. We experimentally demonstrate the efficient and faithful image reconstruction capabilities of DDM from nonlocal patterns, such as speckles from multimode fiber and intensity patterns of second harmonic generation, surpassing the capability of previous state-of-the-art DL algorithms. By embedding Bayesian inference into DDM, we establish a theoretical framework and provide experimental proof of its uncertainty quantification. This advancement ensures the predictive reliability of DDM, avoiding misjudgment in high-stakes scenarios. This versatile and integrable DDM framework can readily extend and improve the efficacy of existing DL-based imaging applications.

eess.IV↗

arXiv2023

Research on CPI Prediction Based on Natural Language Processing

In the past, the seed keywords for CPI prediction were often selected based on empirical summaries of research and literature studies, which were prone to select omitted and invalid variables. In this paper, we design a keyword expansion technique for CPI prediction based on the cutting-edge NLP model, PANGU. We improve the CPI prediction ability using the corresponding web search index. Compared with the unsupervised pre-training and supervised downstream fine-tuning natural language processing models such as BERT and NEZHA, the PANGU model can be expanded to obtain more reliable CPI-generated keywords by its excellent zero-sample learning capability without the limitation of the downstream fine-tuning data set. Finally, this paper empirically tests the keyword prediction ability obtained by this keyword expansion method with historical CPI data.

econ.GN↗

arXiv2022

Measurement of Investment activity in China based on Natural language processing technology

The purpose of this study is to propose a new index to measure and reflect China's investment activity in time, and to analyze the changes of China's investment activity in the past five years. This study first uses the NEZHA model for semantic representation, and expand the indicator system based on semantic similarity. Then we calculate China's investment activity index by using the network search data. This study shows that China's investment activity began to decline in 2019, rebounded for a period of time after the outbreak of COVID-19 in 2020, and then continued to maintain a downward trend. Private investment activity has declined significantly, while government investment activity has increased. Among the provinces in Chinese Mainland, the investment activity of economically developed provinces has decreased significantly, while the investment activity of some economically less developed provinces in the north and south is higher. After the outbreak of COVID-19, the investment period became shorter. Our research will provide timely investment information for the government, decision makers and managers, as well as provide other researchers who also pay attention to investment with a perspective other than investment in fixed asset.

stat.AP↗

arXiv2020

CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking

Expert finding, a popular service provided by many online websites such as Expertise Finder, LinkedIn, and AMiner, is beneficial to seeking candidate qualifications, consultants, and collaborators. However, its quality is suffered from lack of ample sources of expert information. This paper employs AMiner as the basis with an aim at linking any external experts to the counterparts on AMiner. As it is infeasible to acquire sufficient linkages from arbitrary external sources, we explore the problem of zero-shot expert linking. In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner. For evaluation, we first design two intrinsic tasks, author identification and paper clustering, to validate the representation and matching capability endowed by contrastive learning. Then the final external expert linking performance on two genres of external sources also implies the superiority of the adversarial fine-tuning method. Additionally, we show the online deployment of CODE, and continuously improve its online performance via active learning.

cs.IR↗

arXiv2019

JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment

Abstract. Cross-lingual knowledge alignment is the cornerstone in building a comprehensive knowledge graph (KG), which can benefit various knowledge-driven applications. As the structures of KGs are usually sparse, attributes of entities may play an important role in aligning the entities. However, the heterogeneity of the attributes across KGs prevents from accurately embedding and comparing entities. To deal with the issue, we propose to model the interactions between attributes, instead of globally embedding an entity with all the attributes. We further propose a joint framework to merge the alignments inferred from the attributes and the structures. Experimental results show that the proposed model outperforms the state-of-art baselines by up to 38.48% HitRatio@1. The results also demonstrate that our model can infer the alignments between attributes, relationships and values, in addition to entities.

cs.CL↗