arXiv subjects

Di Yu

Publications and source records attributed to Di Yu.

31 records · Page 2Linked to original sources

arXiv2025

Exploiting Label Skewness for Spiking Neural Networks in Federated Learning

The energy efficiency of deep spiking neural networks (SNNs) aligns with the constraints of resource-limited edge devices, positioning SNNs as a promising foundation for intelligent applications leveraging the extensive data collected by these devices. To address data privacy concerns when deploying SNNs on edge devices, federated learning (FL) facilitates collaborative model training by leveraging data distributed across edge devices without transmitting local data to a central server. However, existing FL approaches struggle with label-skewed data across devices, which leads to drift in local SNN models and degrades the performance of the global SNN model. In this paper, we propose a novel framework called FedLEC, which incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias caused by label absence. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to eight state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings.

cs.LG↗

arXiv2025

Edge Intelligence with Spiking Neural Networks

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational resources and centralized data management, the resulting latency, bandwidth consumption, and privacy concerns have exposed critical limitations in cloud-centric paradigms. Brain-inspired computing, particularly Spiking Neural Networks (SNNs), offers a promising alternative by emulating biological neuronal dynamics to achieve low-power, event-driven computation. This survey provides a comprehensive overview of Edge Intelligence based on SNNs (EdgeSNNs), examining their potential to address the challenges of on-device learning, inference, and security in edge scenarios. We present a systematic taxonomy of EdgeSNN foundations, encompassing neuron models, learning algorithms, and supporting hardware platforms. Three representative practical considerations of EdgeSNN are discussed in depth: on-device inference using lightweight SNN models, resource-aware training and updating under non-stationary data conditions, and secure and privacy-preserving issues. Furthermore, we highlight the limitations of evaluating EdgeSNNs on conventional hardware and introduce a dual-track benchmarking strategy to support fair comparisons and hardware-aware optimization. Through this study, we aim to bridge the gap between brain-inspired learning and practical edge deployment, offering insights into current advancements, open challenges, and future research directions. To the best of our knowledge, this is the first dedicated and comprehensive survey on EdgeSNNs, providing an essential reference for researchers and practitioners working at the intersection of neuromorphic computing and edge intelligence.

cs.DC↗

arXiv2025

Frank-Wolfe Recursions for the Emergency Response Problem on Measure Spaces

We consider an optimization problem over measures for emergency response to out-of-hospital cardiac arrest (OHCA), where the goal is to allocate volunteer resources across a spatial region to minimize the probability of death. The problem is infinite-dimensional and poses challenges for analysis and computation. We first establish structural properties, including convexity of the objective functional, compactness of the feasible set, and existence of optimal solutions. We also derive the influence function, which serves as the first-order variational object in our optimization framework. We then adapt and analyze a fully-corrective Frank-Wolfe (fc-FW) algorithm that operates directly on the infinite-dimensional problem without discretization or parametric approximation. We show a form of convergence even when subproblems are not solved to global optimality. Our full implementation of fc-FW demonstrates complex solution structure even in simple discrete cases, reveals nontrivial volunteer allocations in continuous cases, and scales to realistic urban scenarios using OHCA data from the city of Auckland, New Zealand. Finally, we show that when volunteer travel is modeled through the $L_1$ norm, the influence function is piecewise strictly concave, enabling fast computation via support reduction. The proposed framework and analysis extend naturally to a broad class of $P$-means problems.

math.OC↗

arXiv2025

Dendritic Localized Learning: Toward Biologically Plausible Algorithm

Backpropagation is the foundational algorithm for training neural networks and a key driver of deep learning's success. However, its biological plausibility has been challenged due to three primary limitations: weight symmetry, reliance on global error signals, and the dual-phase nature of training, as highlighted by the existing literature. Although various alternative learning approaches have been proposed to address these issues, most either fail to satisfy all three criteria simultaneously or yield suboptimal results. Inspired by the dynamics and plasticity of pyramidal neurons, we propose Dendritic Localized Learning (DLL), a novel learning algorithm designed to overcome these challenges. Extensive empirical experiments demonstrate that DLL satisfies all three criteria of biological plausibility while achieving state-of-the-art performance among algorithms that meet these requirements. Furthermore, DLL exhibits strong generalization across a range of architectures, including MLPs, CNNs, and RNNs. These results, benchmarked against existing biologically plausible learning algorithms, offer valuable empirical insights for future research. We hope this study can inspire the development of new biologically plausible algorithms for training multilayer networks and advancing progress in both neuroscience and machine learning. Our code is available at https://github.com/Lvchangze/Dendritic-Localized-Learning.

cs.NE↗

arXiv2025

ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks

Most edge-cloud collaboration frameworks rely on the substantial computational and storage capabilities of cloud-based artificial neural networks (ANNs). However, this reliance results in significant communication overhead between edge devices and the cloud and high computational energy consumption, especially when applied to resource-constrained edge devices. To address these challenges, we propose ECC-SNN, a novel edge-cloud collaboration framework incorporating energy-efficient spiking neural networks (SNNs) to offload more computational workload from the cloud to the edge, thereby improving cost-effectiveness and reducing reliance on the cloud. ECC-SNN employs a joint training approach that integrates ANN and SNN models, enabling edge devices to leverage knowledge from cloud models for enhanced performance while reducing energy consumption and processing latency. Furthermore, ECC-SNN features an on-device incremental learning algorithm that enables edge models to continuously adapt to dynamic environments, reducing the communication overhead and resource consumption associated with frequent cloud update requests. Extensive experimental results on four datasets demonstrate that ECC-SNN improves accuracy by 4.15%, reduces average energy consumption by 79.4%, and lowers average processing latency by 39.1%.

cs.DC↗

arXiv2024

Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection

Nonlinear dimensionality reduction lacks interpretability due to the absence of source features in low-dimensional embedding space. We propose an interpretable method featMAP to preserve source features by tangent space embedding. The core of our proposal is to utilize local singular value decomposition (SVD) to approximate the tangent space which is embedded to low-dimensional space by maintaining the alignment. Based on the embedding tangent space, featMAP enables the interpretability by locally demonstrating the source features and feature importance. Furthermore, featMAP embeds the data points by anisotropic projection to preserve the local similarity and original density. We apply featMAP to interpreting digit classification, object detection and MNIST adversarial examples. FeatMAP uses source features to explicitly distinguish the digits and objects and to explain the misclassification of adversarial examples. We also compare featMAP with other state-of-the-art methods on local and global metrics.

cs.CV↗

arXiv2023

Symmetry-Based Quantum Circuit Mapping

Quantum circuit mapping is a crucial process in the quantum circuit compilation pipeline, facilitating the transformation of a logical quantum circuit into a list of instructions directly executable on a target quantum system. Recent research has introduced a post-compilation step known as remapping, which seeks to reconfigure the initial circuit mapping to mitigate quantum circuit errors arising from system variability. As quantum processors continue to scale in size, the efficiency of quantum circuit mapping and the overall compilation process has become of paramount importance. In this work, we introduce a quantum circuit remapping algorithm that leverages the intrinsic symmetries in quantum processors, making it well-suited for large-scale quantum systems. This algorithm identifies all topologically equivalent circuit mappings by constraining the search space using symmetries and accelerates the scoring of each mapping using vector computation. Notably, this symmetry-based circuit remapping algorithm exhibits linear scaling with the number of qubits in the target quantum hardware and is proven to be optimal in terms of its time complexity. Moreover, we conduct a comparative analysis against existing methods in the literature, demonstrating the superior performance of our symmetry-based method on state-of-the-art quantum hardware architectures and highlighting the practical utility of our algorithm, particularly for quantum processors with millions of qubits.

quant-ph↗

arXiv2023

Impact of transforming interface geometry on edge states in valley photonic crystals

Topologically protected edge states arise at the interface of two topologically distinct valley photonic crystals. In this work, we investigate how tailoring the interface geometry, specifically from a zigzag interface to a glide plane, profoundly affects these edge states. Near-field measurements demonstrate how this transformation significantly changes the dispersion relation of the edge mode. We observe a transition from gapless edge states to gapped ones, accompanied by the occurrence of slow light within the Brillouin zone, rather than at its edge. Additionally, we simulate the propagation of the modified edge states through a specially designed valley-conserving defect. The simulations show, by monitoring the transmittance of this defect, how the robustness to backscattering gradually decreases, suggesting a disruption of valley-dependent transport. These findings demonstrate how the gradual emergence of valley-dependent gapless edge states in a valley photonic crystal depends on the geometry of its interface.

physics.optics↗

arXiv2023

Using Adamic-Adar Index Algorithm to Predict Volunteer Collaboration: Less is More

Social networks exhibit a complex graph-like structure due to the uncertainty surrounding potential collaborations among participants. Machine learning algorithms possess generic outstanding performance in multiple real-world prediction tasks. However, whether machine learning algorithms outperform specific algorithms designed for graph link prediction remains unknown to us. To address this issue, the Adamic-Adar Index (AAI), Jaccard Coefficient (JC) and common neighbour centrality (CNC) as representatives of graph-specific algorithms were applied to predict potential collaborations, utilizing data from volunteer activities during the Covid-19 pandemic in Shenzhen city, along with the classical machine learning algorithms such as random forest, support vector machine, and gradient boosting as single predictors and components of ensemble learning. This paper introduces that the AAI algorithm outperformed the traditional JC and CNC, and other machine learning algorithms in analyzing graph node attributes for this task.

cs.SI↗

arXiv2022

DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation

Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison. We, therefore, conduct studies from the perspectives of practical theory and experiments, aiming at benchmarking recommendation for rigorous evaluation. Regarding the theoretical study, a series of hyper-factors affecting recommendation performance throughout the whole evaluation chain are systematically summarized and analyzed via an exhaustive review on 141 papers published at eight top-tier conferences within 2017-2020. We then classify them into model-independent and model-dependent hyper-factors, and different modes of rigorous evaluation are defined and discussed in-depth accordingly. For the experimental study, we release DaisyRec 2.0 library by integrating these hyper-factors to perform rigorous evaluation, whereby a holistic empirical study is conducted to unveil the impacts of different hyper-factors on recommendation performance. Supported by the theoretical and experimental studies, we finally create benchmarks for rigorous evaluation by proposing standardized procedures and providing performance of ten state-of-the-arts across six evaluation metrics on six datasets as a reference for later study. Overall, our work sheds light on the issues in recommendation evaluation, provides potential solutions for rigorous evaluation, and lays foundation for further investigation.

cs.IR↗

arXiv2020

Perturbation theory for Maxwell's equations in anisotropic materials with shifting boundaries

Perturbation theory is a kind of estimation method based on theorem of Taylor expansion, and is useful to investigate electromagnetic solutions of small changes. By considering a sharp boundary as a limit of smoothed systems, previous study has solved the problem when applying standard perturbation theory to Maxwell's equations for small shifts in isotropic dielectric interfaces. However, when dealing with anisotropic materials, an approximation is conducted and leads to an unsatisfactory error. Here we develop a modified perturbation theory for small shifts in anisotropically dielectric interfaces. By using optimized smoothing function for each component of permittivity, we obtain a method to calculate the intrinsic frequency shifts of anisotropic permittivity field when boundaries shift, without approximation. Our method shows accurate results when calculating eigenfrequency's shifts in strong-anisotropy materials, and can be widely used for small shifts in anisotropically dielectric interfaces.

physics.comp-ph↗

arXiv2020

Phonon mediated non-equilibrium correlations and entanglement between distant semiconducting qubits

We theoretically study the non-equilibrium correlations and entanglement between distant semiconductor qubits in a one-dimensional coupled-mechanical-resonator chain. Each qubit is defined by a double quantum dot (DQD) and embedded in a mechanical resonator. The two qubits can be coupled, correlated and entangled through phonon transfer along the resonator chain. We calculate the non-equilibrium correlations and steady-state entanglement at different phonon-phonon coupling rates, and find a maximal steady entanglement induced by a population inversion. The results suggest that highly tunable correlations and entanglement can be generated by phonon-qubit hybrid system, which will contribute to the development of mesoscopic physics and solid-state quantum computation.

cond-mat.mes-hall↗

arXiv2019

Automating Data Monitoring: Detecting Structural Breaks in Time Series Data Using Bayesian Minimum Description Length

In modern business modeling and analytics, data monitoring plays a critical role. Nowadays, sophisticated models often rely on hundreds or even thousands of input variables. Over time, structural changes such as abrupt level shifts or trend slope changes may occur among some of these variables, likely due to changes in economy or government policies. As a part of data monitoring, it is important to identify these changepoints, in terms of which variables exhibit such changes, and what time locations do the changepoints occur. Being alerted about the changepoints can help modelers decide if models need modification or rebuilds, while ignoring them may increase risks of model degrading. Simple process control rules often flag too many false alarms because regular seasonal fluctuations or steady upward or downward trends usually trigger alerts. To reduce potential false alarms, we create a novel statistical method based on the Bayesian Minimum Description Length (BMDL) framework to perform multiple change-point detection. Our method is capable of detecting all structural breaks occurred in the past, and automatically handling data with or without seasonality and/or autocorrelation. It is implemented with computation algorithms such as Markov chain Monte Carlo (MCMC), and can be applied to all variables in parallel. As an explainable anomaly detection tool, our changepoint detection method not only triggers alerts, but provides useful information about the structural breaks, such as the times of changepoints, and estimation of mean levels and linear slopes before and after the changepoints. This makes future business analysis and evaluation on the structural breaks easier.

stat.ME↗