Searcharxiv⌕ Search

arXiv subjects

Jiayi Chen

Publications and source records attributed to Jiayi Chen.

135 records · Page 8Linked to original sources
arXiv2022

Quantum phase transition in magnetic nanographenes on a lead superconductor

Quantum spins, referred to the spin operator preserved by full SU(2) symmetry in the absence of the magnetic anistropy, have been proposed to host exotic interactions with superconductivity4. However, spin orbit coupling and crystal field splitting normally cause a significant magnetic anisotropy for d/f-shell spins on surfaces6,9, breaking SU(2) symmetry and fabricating the spins with Ising properties10. Recently, magnetic nanographenes have been proven to host intrinsic quantum magnetism due to their negligible spin orbital coupling and crystal field splitting. Here, we fabricate three atomically precise nanographenes with the same magnetic ground state of spin S=1/2 on Pb(111) through engineering sublattice imbalance in graphene honeycomb lattice. Scanning tunneling spectroscopy reveals the coexistence of magnetic bound states and Kondo screening in such hybridized system. Through engineering the magnetic exchange strength between the unpaired spin in nanographenes and cooper pairs, quantum phase transition from the singlet to the doublet state has been observed, in consistent with quantum models of spins on superconductors. Our work demonstrates delocalized graphene magnetism host highly tunable magnetic bound states with cooper pairs, which can be further developed to study the Majorana bound states and other rich quantum physics of low-dimensional quantum spins on superconductors.

cond-mat.mes-hall↗
arXiv2022

A Competitive Method for Dog Nose-print Re-identification

Vision-based pattern identification (such as face, fingerprint, iris etc.) has been successfully applied in human biometrics for a long history. However, dog nose-print authentication is a challenging problem since the lack of a large amount of labeled data. For that, this paper presents our proposed methods for dog nose-print authentication (Re-ID) task in CVPR 2022 pet biometric challenge. First, considering the problem that each class only with few samples in the training set, we propose an automatic offline data augmentation strategy. Then, for the difference in sample styles between the training and test datasets, we employ joint cross-entropy, triplet and pair-wise circle losses function for network optimization. Finally, with multiple models ensembled adopted, our methods achieve 86.67\% AUC on the test set. Codes are available at https://github.com/muzishen/Pet-ReID-IMAG.

cs.CV↗
arXiv2022

Long-Tail Session-based Recommendation from Calibration

Accurate predictions in session-based recommendations have progressed, but a few studies have focused on skewed recommendation lists caused by popularity bias. Existing models for mitigating popularity bias have attempted to reduce the overconcentration of popular items by amplifying scores of less popular items. However, they normally ignore the users' different preferences toward long-tail items. Thus, we incorporate calibration, where calibrated recommendations reflect the users' interests in recommendation lists with appropriate proportions, to mitigate the popularity bias from the user's perspective. Specifically, we propose a calibration module to predict the ratio of tail items in the recommendation list from the session representation, and align it to the ongoing session. Additionally, we utilize a two-stage curriculum training strategy to improve prediction in the calibration module. Experiments on benchmark datasets show that our model can both achieve the competitive accuracy of recommendation and provide more tail items.

cs.IR↗
arXiv2022

Projective Manifold Gradient Layer for Deep Rotation Regression

Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several works have proposed different regression-friendly rotation representations, very few works have been devoted to improving the gradient backpropagating in the backward pass. In this paper, we propose a manifold-aware gradient that directly backpropagates into deep network weights. Leveraging Riemannian optimization to construct a novel projective gradient, our proposed regularized projective manifold gradient (RPMG) method helps networks achieve new state-of-the-art performance in a variety of rotation estimation tasks. Our proposed gradient layer can also be applied to other smooth manifolds such as the unit sphere. Our project page is at https://jychen18.github.io/RPMG.

cs.CV↗
arXiv2021

HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities

Existing gradient-based meta-learning approaches to few-shot learning assume that all tasks have the same input feature space. However, in the real world scenarios, there are many cases that the input structures of tasks can be different, that is, different tasks may vary in the number of input modalities or data types. Existing meta-learners cannot handle the heterogeneous task distribution (HTD) as there is not only global meta-knowledge shared across tasks but also type-specific knowledge that distinguishes each type of tasks. To deal with task heterogeneity and promote fast within-task adaptions for each type of tasks, in this paper, we propose HetMAML, a task-heterogeneous model-agnostic meta-learning framework, which can capture both the type-specific and globally shared knowledge and can achieve the balance between knowledge customization and generalization. Specifically, we design a multi-channel backbone module that encodes the input of each type of tasks into the same length sequence of modality-specific embeddings. Then, we propose a task-aware iterative feature aggregation network which can automatically take into account the context of task-specific input structures and adaptively project the heterogeneous input spaces to the same lower-dimensional embedding space of concepts. Our experiments on six task-heterogeneous datasets demonstrate that HetMAML successfully leverages type-specific and globally shared meta-parameters for heterogeneous tasks and achieves fast within-task adaptions for each type of tasks.

cs.AI↗
arXiv2020

The ABC130 barrel module prototyping programme for the ATLAS strip tracker

For the Phase-II Upgrade of the ATLAS Detector, its Inner Detector, consisting of silicon pixel, silicon strip and transition radiation sub-detectors, will be replaced with an all new 100 % silicon tracker, composed of a pixel tracker at inner radii and a strip tracker at outer radii. The future ATLAS strip tracker will include 11,000 silicon sensor modules in the central region (barrel) and 7,000 modules in the forward region (end-caps), which are foreseen to be constructed over a period of 3.5 years. The construction of each module consists of a series of assembly and quality control steps, which were engineered to be identical for all production sites. In order to develop the tooling and procedures for assembly and testing of these modules, two series of major prototyping programs were conducted: an early program using readout chips designed using a 250 nm fabrication process (ABCN-25) and a subsequent program using a follow-up chip set made using 130 nm processing (ABC130 and HCC130 chips). This second generation of readout chips was used for an extensive prototyping program that produced around 100 barrel-type modules and contributed significantly to the development of the final module layout. This paper gives an overview of the components used in ABC130 barrel modules, their assembly procedure and findings resulting from their tests.

physics.ins-det↗
arXiv2019

Towards a Unified Evaluation of Explanation Methods without Ground Truth

This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To this end, we design four metrics to evaluate explanation results without ground-truth explanations. Our metrics can be broadly applied to nine benchmark methods of interpreting neural networks, which provides new insights of explanation methods.

cs.LG↗
arXiv2015

Communication Using a Large-Scale Array of Ubiquitous Antennas: A Geometry Approach

The recent trends of densification and centralized signal processing in radio access networks suggest that future networks may comprise ubiquitous antennas coordinated to form a network-wide gigantic array, referred to as the ubiquitous array (UA). In this paper, the UA communication techniques are designed and analyzed based on a geometric model. Specifically, the UA is modeled as a continuous circular/spherical array enclosing target users and free-space propagation is assumed. First, consider the estimation of multiuser UA channels induced by user locations. Given single pilot symbols, a novel channel estimation scheme is proposed that decomposes training signals into Fourier/Laplace series and thereby translates multiuser channel estimation into peak detection of a derive function of location. The process is shown to suppress noise. Moreover, it is proved that estimation error due to interference diminishes with the increasing minimum user-separation distance following the power law, where the exponent is 1/3 and 1 for the circular and spherical UA, respectively. If orthogonal pilot sequences are used, channel estimation is found to be perfect. Next, consider channel-conjugate data transmission that maximizes received signal power. The power of interference between two users is shown to decay with the increasing user-separation distance sub-linearly and super-linearly for the circular and spherical UA, respectively. Furthermore, a novel multiuser precoding design is proposed by exciting different phase modes of the UA and controlling the mode weight factors to null interference. The number of available degrees of freedom for interference nulling using the UA is proved to be proportional to the minimum user-separation distance.

cs.IT↗