Arrow Research search

Author name cluster

Yuan Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers
2 author rows

Possible papers

10

AAAI Conference 2026 Conference Paper

State Mamba: Spatiotemporal EEG State-Space Model with Dynamic Brain Alignment for Cross-Subject Representation

  • Weining Weng
  • Yang Gu
  • Yuan Ma
  • Yuchen Liu
  • Yingwei Zhang
  • Yiqiang Chen

Cross-subject EEG decoding remains a fundamental challenge due to substantial inter-subject variability in brain activity, which hinders the development of subject-independent EEG models. Despite progress in extracting cross-subject invariant features, existing studies neglect the shared neural responses that arise under similar cognitive or emotional states across individuals, limiting their ability to learn generalized and consistent EEG representations. To address the challenges, we propose State Mamba, a novel spatiotemporal EEG state-space model that explicitly models and aligns neural responses and their spatiotemporal state transitions to learn consistent and generalizable representations across subjects. Innovatively, State Mamba theoretically formulates a multi-channel Mamba architecture that jointly models spatial and temporal brain state transitions, supporting principled analysis of neural responses. To enhance spatiotemporal feature coupling, we introduce the LGANN module, which adopts global-local attention to integrate long- and short-term brain activity into a compact EEG representation. Furthermore, we design two self-supervised pretext tasks to extract consistent neural patterns across subjects: (1) representation alignment to align EEG representation, and (2) pattern alignment to align their transition rules under identical conditions, jointly promoting subject-invariant EEG representations. Extensive experiments on three benchmark datasets, FACED, DEAP, and ISRUC, demonstrate the superior performance of State Mamba in cross-subject emotion and sleep recognition tasks, validating its robust generalization capability.

PDF Details DOI

ECAI Conference 2023 Conference Paper

Letting Go of Self-Domain Awareness: Multi-Source Domain-Adversarial Generalization via Dynamic Domain-Weighted Contrastive Transfer Learning

  • Yuan Ma
  • Yiqiang Chen 0001
  • Han Yu 0001
  • Yang Gu 0001
  • Shijie Wen
  • Shuai Guo 0001

Domain generalization (DG), which aims to learn a model that can generalize to an unseen target domain, has recently attracted increasing research interest. A major approach is to learn domain invariant representations to avoid greedily capturing all the correlations found in source domains caused by empirical risk minimization. Nevertheless, overly emphasizing learning of domain invariant representations might lead to learning overly-compressed domain invariant representations, causing confusion of different classes in a same domain. To address this limitation, we introduce a novel dynamic domain-weighted contrastive loss, which maximizes the subdomain differences between different classes especially those belonging to the same domain, while minimizing the average distance between the points of the convex hull of the aligned source domains. We propose Multi-source domain-adversarial generalization via dynamic domain-weighted Contrastive transfer learning (MsCtrl), a novel domain-adversarial generalization framework, which optimizes the distribution alignment of source and potential target subdomains in an adversarial manner under the “control” of the aforementioned contrastive loss. Extensive experiments based on real-world datasets demonstrate significant advantages of MsCtrl over existing state-of-the-art methods.

Details

IROS Conference 2023 Conference Paper

Lightweight Real-Time Detection Model for Multi-Sheep Abnormal Behaviour Based on Yolov7-Tiny

  • Haotian Zhang
  • Yuan Ma
  • Xiaobo Wang
  • Rui Mao 0012
  • Meili Wang 0001

Animal behaviour can reflect the health and physiological stage of the animal. Animal behaviour recognition is a vital part of automated farming systems. Although image-based deep learning algorithms can accurately identify animal behaviour, the lack of data on animal abnormal behaviour makes the practical deployment of models of limited significance. At the same time, the ageing of farm monitoring equipment is also a key factor hindering automated farming. This paper constructs a sheep abnormal behaviour dataset ABSB to address these issues and proposes a lightweight real-time multi-sheep abnormal behaviour detection model YOLOv7-Lrab based on the YOLOv7-tiny network. The abnormal behaviour dataset includes four normal behaviours: standing, lying, eating and drinking, and three abnormal behaviours: lameness, attack and death. In the proposed YOLOv7-Lrab model, the small target detection layer, Coordinate attention module, SPD-Conv and Mobileone module are added compared to YOLOv7-tiny. The experimental results show that with a 7: 3 ratio of training data to test data, 96. 5% recognition accuracy and 95. 5% recall can be achieved, and the model size is only 4. 5MB with fps of 156. The model is compressed to a minimum without loss of accuracy, providing a new idea for deploying deep learning model in practical application scenarios.

Details

FOCS Conference 1994 Conference Paper

On the Design of Reliable Boolean Circuits that Contain Partially Unreliable Gates

  • Daniel J. Kleitman
  • Frank Thomson Leighton
  • Yuan Ma

We investigate a model of gate failure for Boolean circuits in which a faulty gate is restricted to output one of its input values. For some types of gates, the model (which we call the short-circuit model of gate failure) is weaker than the traditional von Neumann model where faulty gates always output precisely the wrong value. Our model has the advantage that it allows us to design Boolean circuits that can tolerate worst-case faults, as well as circuits that have arbitrarily high success probability in the case of random faults. Moreover, the short-circuit model captures a particular type of fault that commonly appears in practice, and it suggests a simple method for performing post-test alterations to circuits that have more severe types of faults. A variety of bounds on the size of fault-tolerant circuits are proved in the paper. Perhaps, the most important is a proof that any k-fault-tolerant circuit for any input-sensitive function using any type of gates (even arbitrarily powerful, multiple-input gates) must have size at least /spl Omega/(k log k/log log k). Obtaining a tight bound on the size of a circuit for computing the AND of two values if up to k of the gates are faulty is one of the central questions left open in the paper. >

Details

FOCS Conference 1993 Conference Paper

Breaking the Theta(n log ^2 n) Barrier for Sorting with Faults (Extended Abstract)

  • Frank Thomson Leighton
  • Yuan Ma

We study the problem of constructing a sorting circuit, network, or PRAM algorithm that is tolerant to faults. For the most part, we focus on fault patterns that are random, e. g. , where the result of each comparison is independently faulty with probability upper-bounded by some constant. All previous fault-tolerant sorting circuits, networks, and parallel algorithms require /spl Omega/(log/sup 2/ n) depth (time) and/or /spl Omega/(nlog/sup 2/ n) comparisons to sort n items. In this paper, we construct a passive-fault-tolerant sorting circuit with O(nlog nloglog n) comparators, a reversal-fault-tolerant sorting network with O(n log/sup log(2)/ /sup 3/ n) comparators, and a deterministic O(log n)-step O(n)-processor EREW PRAM fault-tolerant sorting algorithm. The results are based on a new analysis of the AKS circuit, which uses a much weaker notion of expansion that can be preserved in the presence of faults. Previously, the AKS circuit was not believed to be fault-tolerant because the expansion properties that were believed to be crucial for the performance of the circuit are destroyed by random faults. Extensions of our results for worst-case faults are also presented. >

Details

FOCS Conference 1991 Conference Paper

Highly Fault-Tolerant Sorting Circuits

  • Frank Thomson Leighton
  • Yuan Ma
  • C. Greg Plaxton

The problem of constructing a sorting circuit that will work well even if a constant fraction of its comparators fail at random is addressed. Two types of comparator failure are considered: passive failures, which result in no comparison being made (i. e. , the items being compared are output in the same order that they are input), and destructive failures, which result in the items being output in the reverse of the correct order. In either scenario, it is assumed that each comparator is faulty with some constant probability rho, and a circuit is said to be fault-tolerant if it performs some desired function with high probability given that each comparator fails with probability rho. One passive and two destructive circuits are constructed. >

Details