arXiv subjects

Yanyan Liang

Publications and source records attributed to Yanyan Liang.

39 records · Page 3Linked to original sources

arXiv2020

Identification of a Multi-Dimensional Reaction Coordinate for Crystal Nucleation in $\text{Ni}_3\text{Al}$

Nucleation during solidification in multi-component alloys is a complex process that comprises the competition between different crystalline phases as well as chemical composition and ordering. Here, we combine transition interface sampling with an extensive committor analysis to investigate the atomistic mechanisms during the initial stages of nucleation in $\text{Ni}_3\text{Al}$. The formation and growth of crystalline clusters from the melt are strongly influenced by the interplay between three descriptors: the size, crystallinity, and chemical short-range order of the emerging nuclei. We demonstrate that it is essential to include all three features in a multi-dimensional reaction coordinate to correctly describe the nucleation mechanism, where in particular the chemical short-range order plays a crucial role in the stability of small clusters. The necessity of identifying multi-dimensional reaction coordinates is expected to be of key importance for the atomistic characterization of nucleation processes in complex, multi-component systems.

cond-mat.mtrl-sci↗

arXiv2020

MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning

How to utilize deep learning methods for graph classification tasks has attracted considerable research attention in the past few years. Regarding graph classification tasks, the graphs to be classified may have various graph sizes (i.e., different number of nodes and edges) and have various graph properties (e.g., average node degree, diameter, and clustering coefficient). The diverse property of graphs has imposed significant challenges on existing graph learning techniques since diverse graphs have different best-fit hyperparameters. It is difficult to learn graph features from a set of diverse graphs by a unified graph neural network. This motivates us to use a multiplex structure in a diverse way and utilize a priori properties of graphs to guide the learning. In this paper, we propose MxPool, which concurrently uses multiple graph convolution/pooling networks to build a hierarchical learning structure for graph representation learning tasks. Our experiments on numerous graph classification benchmarks show that our MxPool has superiority over other state-of-the-art graph representation learning methods.

cs.LG↗

arXiv2020

CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing

Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face anti-spoofing benchmarks have limited number of subjects ($\le\negmedspace170$) and modalities ($\leq\negmedspace2$), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and modalities. Specifically, it consists of $1,000$ subjects with $21,000$ videos and each sample has $3$ modalities (i.e., RGB, Depth and IR). We also provide comprehensive evaluation metrics, diverse evaluation protocols, training/validation/testing subsets and a measurement tool, developing a new benchmark for face anti-spoofing. Moreover, we present a novel multi-modal multi-scale fusion method as a strong baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modality across different scales. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at https://sites.google.com/qq.com/face-anti-spoofing/welcome/challengecvpr2019?authuser=0

cs.CV↗