arXiv subjects

Weiguo Zhang

Publications and source records attributed to Weiguo Zhang.

4 recordsLinked to original sources

arXiv2023

Observation of c-axis Magnetization at Low Temperatures in Weak Ferromagnet FeBO$_3$ Reveals a Spin-Reorientation Transition

The weak ferromagnet FeBO$_3$ is well known for being a unique system for modelling and testing magnetic dynamics primarily due to relatively simple and localized magnetic structure and its interesting spin wave dynamics. At room temperature, it has slightly canted iron moments lying in the a-b plane that result in a strong antiferromagnetic moment and a weak ferromagnetic moment, which results in pronounced ferromagnetic and antiferromagnetic spin modes. However, some previous studies have shown unusual low-temperature behavior that suggests a phase transition. By performing low-temperature magnetization measurements, both in bulk and on the mesoscale, we have observed a low temperature magnetic texture in this material in which a large c-axis magnetization occurs. Magnetic fields along the c-axis as high as 1300 Oe were observed close to the sample surface. This presents evidence for the onset of a Morin transition or another type of spin-reorientation phase transition wherein the Fe3+ moments would acquire a c-axis component to their canting below a critical temperature. The observation of this c-axis magnetization suggests that there is a different ground state in this material than has been previously expected and could be due to as yet unexplored intricacies of the Dzyaloshinskii-Moriya interaction.

cond-mat.str-el↗

arXiv2022

Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems

As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, auto-encoder and graph neural networks. However, the majority of existing collaborative filtering systems are not well designed to handle missing data. Particularly, in order to inject the negative signals in the training phase, these solutions largely rely on negative sampling from unobserved user-item interactions and simply treating them as negative instances, which brings the recommendation performance degradation. To address the issues, we develop a Collaborative Reflection-Augmented Autoencoder Network (CRANet), that is capable of exploring transferable knowledge from observed and unobserved user-item interactions. The network architecture of CRANet is formed of an integrative structure with a reflective receptor network and an information fusion autoencoder module, which endows our recommendation framework with the ability of encoding implicit user's pairwise preference on both interacted and non-interacted items. Additionally, a parametric regularization-based tied-weight scheme is designed to perform robust joint training of the two-stage CRANet model. We finally experimentally validate CRANet on four diverse benchmark datasets corresponding to two recommendation tasks, to show that debiasing the negative signals of user-item interactions improves the performance as compared to various state-of-the-art recommendation techniques. Our source code is available at https://github.com/akaxlh/CRANet.

cs.IR↗

arXiv2020

Layer-Wise Adaptive Updating for Few-Shot Image Classification

Few-shot image classification (FSIC), which requires a model to recognize new categories via learning from few images of these categories, has attracted lots of attention. Recently, meta-learning based methods have been shown as a promising direction for FSIC. Commonly, they train a meta-learner (meta-learning model) to learn easy fine-tuning weight, and when solving an FSIC task, the meta-learner efficiently fine-tunes itself to a task-specific model by updating itself on few images of the task. In this paper, we propose a novel meta-learning based layer-wise adaptive updating (LWAU) method for FSIC. LWAU is inspired by an interesting finding that compared with common deep models, the meta-learner pays much more attention to update its top layer when learning from few images. According to this finding, we assume that the meta-learner may greatly prefer updating its top layer to updating its bottom layers for better FSIC performance. Therefore, in LWAU, the meta-learner is trained to learn not only the easy fine-tuning model but also its favorite layer-wise adaptive updating rule to improve its learning efficiency. Extensive experiments show that with the layer-wise adaptive updating rule, the proposed LWAU: 1) outperforms existing few-shot classification methods with a clear margin; 2) learns from few images more efficiently by at least 5 times than existing meta-learners when solving FSIC.

cs.CV↗

arXiv2020

Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning

Recently, meta-learning has been shown as a promising way to solve few-shot learning. In this paper, inspired by the human cognition process which utilizes both prior-knowledge and vision attention in learning new knowledge, we present a novel paradigm of meta-learning approach with three developments to introduce attention mechanism and prior-knowledge for meta-learning. In our approach, prior-knowledge is responsible for helping meta-learner expressing the input data into high-level representation space, and attention mechanism enables meta-learner focusing on key features of the data in the representation space. Compared with existing meta-learning approaches that pay little attention to prior-knowledge and vision attention, our approach alleviates the meta-learner's few-shot cognition burden. Furthermore, a Task-Over-Fitting (TOF) problem, which indicates that the meta-learner has poor generalization on different K-shot learning tasks, is discovered and we propose a Cross-Entropy across Tasks (CET) metric to model and solve the TOF problem. Extensive experiments demonstrate that we improve the meta-learner with state-of-the-art performance on several few-shot learning benchmarks, and at the same time the TOF problem can also be released greatly.

cs.CV↗