arXiv subjects

Zhonghua Zhao

Publications and source records attributed to Zhonghua Zhao.

5 recordsLinked to original sources

arXiv2026

CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG

EEG-based neural decoding models often fail to generalize across acquisition sites due to structured, site-dependent biases implicitly exploited during training. We reformulate cross-site clinical EEG learning as a bias-factorized generalization problem, in which domain shifts arise from multiple interacting sources. We identify three fundamental bias factors and propose a general training framework that mitigates their influence through data standardization and representation-level constraints. We construct a standardized multi-site EEG benchmark for Major Depressive Disorder and introduce CRCC, a two-stage training paradigm combining encoder-decoder pretraining with joint fine-tuning via cross-subject/site contrastive learning and site-adversarial optimization. CRCC consistently outperforms state-of-the-art baselines and achieves a 10.7 percentage-point improvement in balanced accuracy under strict zero-shot site transfer, demonstrating robust generalization to unseen environments.

q-bio.NC↗

arXiv2025

Meta-Computing Enhanced Federated Learning in IIoT: Satisfaction-Aware Incentive Scheme via DRL-Based Stackelberg Game

The Industrial Internet of Things (IIoT) leverages Federated Learning (FL) for distributed model training while preserving data privacy, and meta-computing enhances FL by optimizing and integrating distributed computing resources, improving efficiency and scalability. Efficient IIoT operations require a trade-off between model quality and training latency. Consequently, a primary challenge of FL in IIoT is to optimize overall system performance by balancing model quality and training latency. This paper designs a satisfaction function that accounts for data size, Age of Information (AoI), and training latency for meta-computing. Additionally, the satisfaction function is incorporated into the utility function to incentivize IIoT nodes to participate in model training. We model the utility functions of servers and nodes as a two-stage Stackelberg game and employ a deep reinforcement learning approach to learn the Stackelberg equilibrium. This approach ensures balanced rewards and enhances the applicability of the incentive scheme for IIoT. Simulation results demonstrate that, under the same budget constraints, the proposed incentive scheme improves utility by at least 23.7% compared to existing FL schemes without compromising model accuracy.

cs.LG↗

arXiv2017

Learning Social Image Embedding with Deep Multimodal Attention Networks

Learning social media data embedding by deep models has attracted extensive research interest as well as boomed a lot of applications, such as link prediction, classification, and cross-modal search. However, for social images which contain both link information and multimodal contents (e.g., text description, and visual content), simply employing the embedding learnt from network structure or data content results in sub-optimal social image representation. In this paper, we propose a novel social image embedding approach called Deep Multimodal Attention Networks (DMAN), which employs a deep model to jointly embed multimodal contents and link information. Specifically, to effectively capture the correlations between multimodal contents, we propose a multimodal attention network to encode the fine-granularity relation between image regions and textual words. To leverage the network structure for embedding learning, a novel Siamese-Triplet neural network is proposed to model the links among images. With the joint deep model, the learnt embedding can capture both the multimodal contents and the nonlinear network information. Extensive experiments are conducted to investigate the effectiveness of our approach in the applications of multi-label classification and cross-modal search. Compared to state-of-the-art image embeddings, our proposed DMAN achieves significant improvement in the tasks of multi-label classification and cross-modal search.

cs.MM↗

arXiv2016

Remarks on PBW bases of Ringel-Hall algebras of cyclic quivers

In this paper, we give a recursive formula for the interesting PBW basis $E_{A}$ of composition subalgebras of Ringel-Hall algebras $\fkH_\vartri(n)$ of cyclic quivers after \cite{DengDuXiao2007generic}, and another construction of canonical bases of $\U_v^+(\wih{\fks\fkl}_n)$ from the monomial bases $m^{(A)}$ follow \cite{DuZhaomultiplication}. As an application, we will determined all the canonical basis of $\U_v^+(\wih{\fks\fkl}_2)$ associated with modules of Lowery length $\leqs3$. Finally, we will discuss the relation of canonical bases of Ringel-Hall algebras and those of affine quantum Schur algebras.

math.RT↗

arXiv2016

Multiplicaton formulas and canonical basis for quantum affine gl_n

We will give a representation-theoretic proof for the multiplication formula in the Ringel-Hall algebra ${\frak H}_Δ(n)$ of a cyclic quiver $Δ(n)$ given in \cite[Thm~4.5]{DuFu2015quantum}. As a first application, we see immediately the existence of Hall polynomials for cyclic quivers, a fact established in \cite{Guo1995hallpoly} and \cite{Ringel1993composition}, and derive a recursive formula to compute them. We will further use the formula and the construction of certain monomial base for ${\mathfrak H}_Δ(n)$ given in \cite{DengDuXiao2007generic}, together with the double Ringel--Hall algebra realisation of the quantum loop algebra $U_v(\hat{gl}_n)$ in \cite{DengDuFu2012double}, to develop some algorithms and to compute the canonical basis for $U_v(\hat{gl}_n)^+$. As examples, we will show explicitly the part of the canonical basis associated with modules of Lowey length at most $2$ for the quantum group $U_v(\hat{gl}_n)$.

math.QA↗