Searcharxiv⌕ Search

arXiv subjects

Yang Yan

Publications and source records attributed to Yang Yan.

30 records · Page 2Linked to original sources
arXiv2022

Prediction of superconducting properties of materials based on machine learning models

The application of superconducting materials is becoming more and more widespread. Traditionally, the discovery of new superconducting materials relies on the experience of experts and a large number of "trial and error" experiments, which not only increases the cost of experiments but also prolongs the period of discovering new superconducting materials. In recent years, machine learning has been increasingly applied to materials science. Based on this, this manuscript proposes the use of XGBoost model to identify superconductors; the first application of deep forest model to predict the critical temperature of superconductors; the first application of deep forest to predict the band gap of materials; and application of a new sub-network model to predict the Fermi energy level of materials. Compared with our known similar literature, all the above algorithms reach state-of-the-art. Finally, this manuscript uses the above models to search the COD public dataset and identify 50 candidate superconducting materials with possible critical temperature greater than 90 K.

cond-mat.supr-con↗
arXiv2022

InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER

Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for downstream tasks. However, existing prompt templates are mostly designed for sentence-level tasks and are inappropriate for sequence labeling objectives. To address the above issue, we propose a multi-task instruction-based generative framework, named InstructionNER, for low-resource named entity recognition. Specifically, we reformulate the NER task as a generation problem, which enriches source sentences with task-specific instructions and answer options, then inferences the entities and types in natural language. We further propose two auxiliary tasks, including entity extraction and entity typing, which enable the model to capture more boundary information of entities and deepen the understanding of entity type semantics, respectively. Experimental results show that our method consistently outperforms other baselines on five datasets in few-shot settings.

cs.CL↗
arXiv2021

ISHNE: Influence Self-attention for Heterogeneous Network Embedding

In recent years, Graph Neural Networks has received enormous attention from academia for its huge potential of modeling the network traits such as macrostructure and single node attributes. However, prior mainstream works mainly focus on homogeneous network and lack the capacity to characterize the network heterogeneous property. Besides, most previous literature cannot model the influence under microscope vision, making it infeasible to model the joint relation between the heterogeneity and mutual interaction within multiple relation type. In this paper, we propose an Influence Self-attention network to address the difficulties mentioned above. To model heterogeneity and mutual interaction, we redesign attention mechanism with influence factor on the single-type relation level, which learns the importance coefficient from its adjacent neighbors under the same meta-path based patterns. To incorporate the heterogeneous meta-path in a unified dimension, we developed a self-attention based framework for meta-path relation fusion according to the learned meta-path coefficient. Our experimental results demonstrate that our framework not only achieve higher results than current state-of-the-art baselines, but also show promising vision on depicting heterogeneous interactive relations under complicated network structure.

cs.SI↗
arXiv2020

Asymptotically optimal codebooks derived from generalised bent functions

Codebooks are required to have small inner-product correlation in many practical applications, such as direct spread code division multiple access communications, space-time codes and compressed sensing. In general, it is difficult to construct optimal codebooks. In this paper, two kinds of codebooks are presented and proved to optimally optimal with respect to the welch bound. Additionally, the constructed codebooks in this paper have new parameters.

cs.IT↗
arXiv2020

Multisequences with high joint nonlinear complexity from function fields

Multisequences over finite fields play a pushing role in the applications that relate to parallelization, such as word-based stream ciphers and pseudorandom vector generation. It is interesting to study the complexity measures for multisequences. In this paper, we propose three constructions of multisequences over finite fields from rational function fields and Hermitian function fields. We also analyze the joint nonlinear complexity of these multisequences. Moreover, the length and dimension of these multisequences are flexible.

cs.IT↗
arXiv2019

Analysis of Two-Dimensional Feedback Systems over Networks Using Dissipativity

This paper investigates the closed-loop $\mathcal{L}_2$ stability of two-dimensional (2-D) feedback systems across a digital communication network by introducing the tool of dissipativity. First, sampling of a continuous 2-D system is considered and an analytical characterization of the $QSR$-dissipativity of the sampled system is presented. Next, the input-feedforward output-feedback passivity (IF-OFP), a simplified form of $QSR$-dissipativity, is utilized to study the framework of feedback interconnection of two 2-D systems over networks. Then, the effects of signal quantization in communication links on dissipativity degradation of the 2-D feedback quantized system is analyzed. Additionally, an event-triggered mechanism is developed for 2-D networked control systems while maintaining $\mathcal{L}_2$ stability of the closed-loop system. In the end, an illustrative example is provided.

eess.SY↗
arXiv2019

Jointly Adversarial Network to Wavelength Compensation and Dehazing of Underwater Images

Severe color casts, low contrast and blurriness of underwater images caused by light absorption and scattering result in a difficult task for exploring underwater environments. Different from most of previous underwater image enhancement methods that compute light attenuation along object-camera path through hazy image formation model, we propose a novel jointly wavelength compensation and dehazing network (JWCDN) that takes into account the wavelength attenuation along surface-object path and the scattering along object-camera path simultaneously. By embedding a simplified underwater formation model into generative adversarial network, we can jointly estimates the transmission map, wavelength attenuation and background light via different network modules, and uses the simplified underwater image formation model to recover degraded underwater images. Especially, a multi-scale densely connected encoder-decoder network is proposed to leverage features from multiple layers for estimating the transmission map. To further improve the recovered image, we use an edge preserving network module to enhance the detail of the recovered image. Moreover, to train the proposed network, we propose a novel underwater image synthesis method that generates underwater images with inherent optical properties of different water types. The synthesis method can simulate the color, contrast and blurriness appearance of real-world underwater environments simultaneously. Extensive experiments on synthetic and real-world underwater images demonstrate that the proposed method yields comparable or better results on both subjective and objective assessments, compared with several state-of-the-art methods.

eess.IV↗
arXiv2019

Purifying Real Images with an Attention-guided Style Transfer Network for Gaze Estimation

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images compared to real images, the desired performance cannot be achieved. Real images consist of multiple forms of light orientation, while synthetic images consist of a uniform light orientation. These features are considered to be characteristic of outdoor and indoor scenes, respectively. To solve this problem, the previous method learned a model to improve the realism of the synthetic image. Different from the previous methods, this paper try to purify real image by extracting discriminative and robust features to convert outdoor real images to indoor synthetic images. In this paper, we first introduce the segmentation masks to construct RGB-mask pairs as inputs, then we design a attention-guided style transfer network to learn style features separately from the attention and bkgd(background) region , learn content features from full and attention region. Moreover, we propose a novel region-level task-guided loss to restrain the features learnt from style and content. Experiments were performed using mixed studies (qualitative and quantitative) methods to demonstrate the possibility of purifying real images in complex directions. We evaluate the proposed method on three public datasets, including LPW, COCO and MPIIGaze. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results.

cs.CV↗
arXiv2016

A family of linear codes with three weights

Recently, linear codes constructed by defining sets have attracted a lot of study, and many optimal linear codes with a few weights have been produced. The objective of this paper is to present a class of binary linear codes with three weights.

cs.IT↗
arXiv2016

Linear complexity of generalized cyclotomic sequences of order 4 over F_l

Generalized cyclotomic sequences of period pq have several desirable randomness properties if the two primes p and q are chosen properly. In particular,Ding deduced the exact formulas for the autocorrelation and the linear complexity of these sequences of order 2. In this paper, we consider the generalized sequences of order 4. Under certain conditions, the linear complexity of these sequences of order 4 is developed over a finite field F_l. Results show that in many cases they have high linear complexity.

cs.IT↗
arXiv2016

Binary linear codes with at most 4 weights

For the past decades, linear codes with few weights have been widely studied, since they have applications in space communications, data storage and cryptography. In this paper, a class of binary linear codes is constructed and their weight distribution is determined. Results show that they are at most 4-weight linear codes. Additionally, these codes can be used in secret sharing schemes.

cs.IT↗