arXiv subjects

Wenwu Yu

Publications and source records attributed to Wenwu Yu.

34 records · Page 2Linked to original sources

arXiv2026

CCMamba: Topologically-Informed Selective State-Space Networks on Combinatorial Complexes for Higher-Order Graph Learning

Topological deep learning has emerged as a powerful paradigm for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to capture. While combinatorial complexes (CCs) offer a unified topological foundation for the higher-order graph learning, existing topological deep learning methods rely heavily on local message passing and attention mechanisms. These suffer from quadratic complexity and local neighborhood constraints, limiting their scalability and capacity for rank-aware, long-range dependency modeling. To overcome these challenges, we propose Combinatorial Complex Mamba (CCMamba), the first unified Mamba-based neural framework for learning on combinatorial complexes. CCMamba reformulates higher-order message passing as a selective state-space modeling problem by linearizing multi-rank incidence relations into structured, rank-aware sequences. This architecture enables adaptive, directional, and long-range information propagation in linear time bypassing the scalability bottlenecks of self-attention. Theoretically, we further establish that the expressive power of CCMamba is upper-bounded by the 1-dimensional combinatorial complex Weisfeiler-Lehman (1-CCWL) test. Extensive experiments across graph, hypergraph, and simplicial benchmarks demonstrate that CCMamba consistently outperforms existing methods while exhibiting superior scalability and remarkable robustness against over-smoothing in deep architectures.

cs.LG↗

arXiv2026

TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Prediction

Dynamic link prediction plays a crucial role in diverse applications including social network analysis, communication forecasting, and financial modeling. While recent Transformer-based approaches have demonstrated promising results in temporal graph learning, their performance remains limited when capturing complex multi-scale temporal dynamics. In this paper, we propose TFWaveFormer, a novel Transformer architecture that integrates temporal-frequency analysis with multi-resolution wavelet decomposition to enhance dynamic link prediction. Our framework comprises three key components: (i) a temporal-frequency coordination mechanism that jointly models temporal and spectral representations, (ii) a learnable multi-resolution wavelet decomposition module that adaptively extracts multi-scale temporal patterns through parallel convolutions, replacing traditional iterative wavelet transforms, and (iii) a hybrid Transformer module that effectively fuses local wavelet features with global temporal dependencies. Extensive experiments on benchmark datasets demonstrate that TFWaveFormer achieves state-of-the-art performance, outperforming existing Transformer-based and hybrid models by significant margins across multiple metrics. The superior performance of TFWaveFormer validates the effectiveness of combining temporal-frequency analysis with wavelet decomposition in capturing complex temporal dynamics for dynamic link prediction tasks.

cs.LG↗

arXiv2026

Spatio-Temporal Graphical Counterfactuals: An Overview

Counterfactual thinking is a crucial yet challenging topic for artificial intelligence to learn knowledge from data and ultimately improve performance for new scenarios. Many research works, including the Potential Outcome Model (POM) and the Structural Causal Model (SCM), have been proposed to address this. However, their modeling, theoretical foundations, and application approaches often differ. Moreover, there is a lack of graphical approaches for inferring spatio-temporal counterfactuals, that account for spatial and temporal interactions among multiple units. Thus, in this work, we aim to present a survey that compares and discusses different counterfactual models, theories and approaches. Additionally, we propose a unified graphical causal framework to infer spatio-temporal counterfactuals.

cs.AI↗

arXiv2025

Distributed scalable coupled policy algorithm for networked multi-agent reinforcement learning

This paper studies networked multi-agent reinforcement learning (NMARL) with interdependent rewards and coupled policies. In this setting, each agent's reward depends on its own state-action pair as well as those of its direct neighbors, and each agent's policy is parameterized by its local parameters together with those of its $κ_{p}$-hop neighbors, with $κ_{p}\geq 1$ denoting the coupled radius. The objective of the agents is to collaboratively optimize their policies to maximize the discounted average cumulative reward. To address the challenge of interdependent policies in collaborative optimization, we introduce a novel concept termed the neighbors' averaged $Q$-function and derive a new expression for the coupled policy gradient. Based on these theoretical foundations, we develop a distributed scalable coupled policy (DSCP) algorithm, where each agent relies only on the state-action pairs of its $κ_{p}$-hop neighbors and the rewards of its $(κ_{p}+1)$-hop neighbors. Specially, in the DSCP algorithm, we employ a geometric 2-horizon sampling method that does not require storing a full $Q$-table to obtain an unbiased estimate of the coupled policy gradient. Moreover, each agent interacts exclusively with its direct neighbors to obtain accurate policy parameters, while maintaining local estimates of other agents' parameters to execute its local policy and collect samples for optimization. These estimates and policy parameters are updated via a push-sum protocol, enabling distributed coordination of policy updates across the network. We prove that the joint policy produced by the proposed algorithm converges to a first-order stationary point of the objective function. Finally, the effectiveness of DSCP algorithm is demonstrated through simulations in a robot path planning environment, showing clear improvement over state-of-the-art methods.

cs.MA↗

arXiv2025

The Robustness of Differentiable Causal Discovery in Misspecified Scenarios

Causal discovery aims to learn causal relationships between variables from targeted data, making it a fundamental task in machine learning. However, causal discovery algorithms often rely on unverifiable causal assumptions, which are usually difficult to satisfy in real-world data, thereby limiting the broad application of causal discovery in practical scenarios. Inspired by these considerations, this work extensively benchmarks the empirical performance of various mainstream causal discovery algorithms, which assume i.i.d. data, under eight model assumption violations. Our experimental results show that differentiable causal discovery methods exhibit robustness under the metrics of Structural Hamming Distance and Structural Intervention Distance of the inferred graphs in commonly used challenging scenarios, except for scale variation. We also provide the theoretical explanations for the performance of differentiable causal discovery methods. Finally, our work aims to comprehensively benchmark the performance of recent differentiable causal discovery methods under model assumption violations, and provide the standard for reasonable evaluation of causal discovery, as well as to further promote its application in real-world scenarios.

cs.LG↗

arXiv2025

Critical Nodes Identification in Complex Networks: A Survey

Complex networks have become essential tools for understanding diverse phenomena in social systems, traffic systems, biomolecular systems, and financial systems. Identifying critical nodes is a central theme in contemporary research, serving as a vital bridge between theoretical foundations and practical applications. Nevertheless, the intrinsic complexity and structural heterogeneity characterizing real-world networks, with particular emphasis on dynamic and higher-order networks, present substantial obstacles to the development of universal frameworks for critical node identification. This paper provides a comprehensive review of critical node identification techniques, categorizing them into seven main classes: centrality, critical nodes deletion problem, influence maximization, network control, artificial intelligence, higher-order and dynamic methods. Our review bridges the gaps in existing surveys by systematically classifying methods based on their methodological foundations and practical implications, and by highlighting their strengths, limitations, and applicability across different network types. Our work enhances the understanding of critical node research by identifying key challenges, such as algorithmic universality, real-time evaluation in dynamic networks, analysis of higher-order structures, and computational efficiency in large-scale networks. The structured synthesis consolidates current progress and highlights open questions, particularly in modeling temporal dynamics, advancing efficient algorithms, integrating machine learning approaches, and developing scalable and interpretable metrics for complex systems.

cs.SI↗

arXiv2025

Identifying Unique Spatial-Temporal Bayesian Network without Markov Equivalence

Identifying vanilla Bayesian network to model spatial-temporal causality can be a critical yet challenging task. Different Markovian-equivalent directed acyclic graphs would be identified if the identifiability is not satisfied. To address this issue, Directed Cyclic Graph is proposed to drop the directed acyclic constraint. But it does not always hold, and cannot model dynamical time-series process. Then, Full Time Graph is proposed with introducing high-order time delay. Full Time Graph has no Markov equivalence class by assuming no instantaneous effects. But, it also assumes that the causality is invariant with varying time, that is not always satisfied in the spatio-temporal scenarios. Thus, in this work, a Spatial-Temporal Bayesian Network (STBN) is proposed to theoretically model the spatial-temporal causality from the perspective of information transfer. STBN explains the disappearance of network structure $X\rightarrow Z \rightarrow Y$ and $X\leftarrow Z \leftarrow Y$ by the principle of information path blocking. And finally, the uniqueness of STBN is proved. Based on this, a High-order Causal Entropy (HCE) algorithm is also proposed to uniquely identify STBN under time complexity $\mathcal{O}(n^3τ_{max})$, where $n$ is the number of variables and $τ_{max}$ is the maximum time delay. Numerical experiments are conducted with comparison to other baseline algorithms. The results show that HCE algorithm obtains state-of-the-art identification accuracy. The code is available at https://github.com/KMY-SEU/HCE.

cs.AI↗

arXiv2025

Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning

This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer from poor expression due to linear function approximation, we propose a distributed neural policy gradient algorithm that features two innovatively designed neural networks, specifically for the approximate Q-functions and policy functions of agents. This distributed neural policy gradient algorithm consists of two key components: the distributed critic step and the decentralized actor step. In the distributed critic step, agents receive the approximate Q-function parameters from their neighboring agents via a time-varying communication networks to collaboratively evaluate the joint policy. In contrast, in the decentralized actor step, each agent updates its local policy parameter solely based on its own approximate Q-function. In the convergence analysis, we first establish the global convergence of agents for the joint policy evaluation in the distributed critic step. Subsequently, we rigorously demonstrate the global convergence of the overall distributed neural policy gradient algorithm with respect to the objective function. Finally, the effectiveness of the proposed algorithm is demonstrated by comparing it with a centralized algorithm through simulation in the robot path planning environment.

cs.MA↗

arXiv2025

Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs

Spatio-temporal prediction is a pivotal task with broad applications in traffic management, climate monitoring, energy scheduling, etc. However, existing methodologies often struggle to balance model expressiveness and computational efficiency, especially when scaling to large real-world datasets. To tackle these challenges, we propose STH-SepNet (Spatio-Temporal Hypergraph Separation Networks), a novel framework that decouples temporal and spatial modeling to enhance both efficiency and precision. Therein, the temporal dimension is modeled using lightweight large language models, which effectively capture low-rank temporal dynamics. Concurrently, the spatial dimension is addressed through an adaptive hypergraph neural network, which dynamically constructs hyperedges to model intricate, higher-order interactions. A carefully designed gating mechanism is integrated to seamlessly fuse temporal and spatial representations. By leveraging the fundamental principles of low-rank temporal dynamics and spatial interactions, STH-SepNet offers a pragmatic and scalable solution for spatio-temporal prediction in real-world applications. Extensive experiments on large-scale real-world datasets across multiple benchmarks demonstrate the effectiveness of STH-SepNet in boosting predictive performance while maintaining computational efficiency. This work may provide a promising lightweight framework for spatio-temporal prediction, aiming to reduce computational demands and while enhancing predictive performance. Our code is avaliable at https://github.com/SEU-WENJIA/ST-SepNet-Lightweight-LLMs-Meet-Adaptive-Hypergraphs.

cs.LG↗

arXiv2023

Razumikhin-type ISS Lyapunov function and small gain theorem for discrete time time-delay systems with application to a biased min-consensus protocol

This paper considers small gain theorems for the global asymptotic and exponential input-to-state stability for discrete time time-delay systems using Razumikhin-type Lyapunov function. Among other things, unlike the existing literature, it provides both necessary and sufficient conditions for exponential input-to-state stability in terms of the Razumikhin-type Lyapunov function and the small gain theorem. Previous necessary ad sufficient conditions were with the more computationally onerous, Krasovskii-type Lyapunov functions. The result finds application in the robust stability analysis of a graph-based distributed algorithm, namely, the biased min-consensus protocol, which can be used to compute the length of the shortest path from each node to its nearest source in a graph. We consider the biased min-consensus protocol under perturbations that are common in communication networks, including noise, delay and asynchronous communication. By converting such a perturbed protocol into a discrete time time-delay nonlinear system, we prove its exponential input-to-state stability under perturbations using our Razumikhin-type Lyapunov-based small gain theorem. Simulations are provided to verify the theoretical results.

eess.SY↗

arXiv2023

Interpretable System Identification and Long-term Prediction on Time-Series Data

Time-series prediction has drawn considerable attention during the past decades fueled by the emerging advances of deep learning methods. However, most neural network based methods lack interpretability and fail in extracting the hidden mechanism of the targeted physical system. To overcome these shortcomings, an interpretable sparse system identification method without any prior knowledge is proposed in this study. This method adopts the Fourier transform to reduces the irrelevant items in the dictionary matrix, instead of indiscriminate usage of polynomial functions in most system identification methods. It shows an interpretable system representation and greatly reduces computing cost. With the adoption of $l_1$ norm in regularizing the parameter matrix, a sparse description of the system model can be achieved. Moreover, Three data sets including the water conservancy data, global temperature data and financial data are used to test the performance of the proposed method. Although no prior knowledge was known about the physical background, experimental results show that our method can achieve long-term prediction regardless of the noise and incompleteness in the original data more accurately than the widely-used baseline data-driven methods. This study may provide some insight into time-series prediction investigations, and suggests that an white-box system identification method may extract the easily overlooked yet inherent periodical features and may beat neural-network based black-box methods on long-term prediction tasks.

cs.LG↗

arXiv2023

A Distributed control framework for the optimal operation of DC microgrids

In this paper we propose an original distributed control framework for DC mcirogrids. We first formulate the (optimal) control objectives as an aggregative game suitable for the energy trading market. Then, based on the dual theory, we analyze the equivalent distributed optimal condition for the proposed aggregative game and design a distributed control scheme to solve it. By interconnecting the DC mcirogrid and the designed distributed control system in a power preserving way, we steer the DC microgrid's state to the desired optimal equilibrium, satisfying a predefined set of local and coupling constraints. Finally, based on the singular perturbation system theory, we analyze the convergence of the closed-loop system. The simulation results show excellent performance of the proposed control framework.

eess.SY↗

arXiv2022

Distributed Algorithm Over Time-Varying Unbalanced Topologies for Optimization Problem Subject to Multiple Local Constraints

This paper studies the distributed optimization problem with possibly nonidentical local constraints, where its global objective function is composed of $N$ convex functions. The aim is to solve the considered optimization problem in a distributed manner over time-varying unbalanced directed topologies by using only local information and performing only local computations. Towards this end, a new distributed discrete-time algorithm is developed by synthesizing the row stochastic matrices sequence and column stochastic matrices sequence analysis technique. Furthermore, for the developed distributed discrete-time algorithm, its convergence property to the optimal solution as well as its convergence rate are established under some mild assumptions. Numerical simulations are finally presented to verify the theoretical results.

math.OC↗

arXiv2020

A Separation-Based Methodology to Consensus Tracking of Switched High-Order Nonlinear Multi-Agent Systems

This work investigates a reduced-complexity adaptive methodology to consensus tracking for a team of uncertain high-order nonlinear systems with switched (possibly asynchronous) dynamics. It is well known that high-order nonlinear systems are intrinsically challenging as feedback linearization and backstepping methods successfully developed for low-order systems fail to work. At the same time, even the adding-one power-integrator methodology, well explored for the single-agent high-order case, presents some complexity issues and is unsuited for distributed control. At the core of the proposed distributed methodology is a newly proposed definition for separable functions: this definition allows the formulation of a separation-based lemma to handle the high-order terms with reduced complexity in the control design. Complexity is reduced in a twofold sense: the control gain of each virtual control law does not have to be incorporated in the next virtual control law iteratively, thus leading to a simpler expression of the control laws; the order of the virtual control gains increases only proportionally (rather than exponentially) with the order of the systems, dramatically reducing high-gain issues.

cs.MA↗

arXiv2012

An Overview of Recent Progress in the Study of Distributed Multi-agent Coordination

This article reviews some main results and progress in distributed multi-agent coordination, focusing on papers published in major control systems and robotics journals since 2006. Distributed coordination of multiple vehicles, including unmanned aerial vehicles, unmanned ground vehicles and unmanned underwater vehicles, has been a very active research subject studied extensively by the systems and control community. The recent results in this area are categorized into several directions, such as consensus, formation control, optimization, task assignment, and estimation. After the review, a short discussion section is included to summarize the existing research and to propose several promising research directions along with some open problems that are deemed important for further investigations.

math.OC↗

arXiv2009

Flocking of Multi-agent Dynamical Systems Based on Pseudo-leader Mechanism

Flocking behavior of multiple agents can be widely observed in nature such as schooling fish and flocking birds. Recent literature has proposed the possibility that flocking is possible even only a small fraction of agents are informed of the desired position and velocity. However, it is still a challenging problem to determine which agents should be informed or have the ability to detect the desired information. This paper aims to address this problem. By combining the ideas of virtual force and pseudo-leader mechanism, where a pseudo-leader represents an agent who can detect the desired information, we propose a scheme for choosing pseudo-leaders in a multi-agent group. The presented scheme can be applied to a multi-agent group even with an unconnected or switching neighbor graph. Experiments are given to show that the methods presented in this paper are of high accuracy and perform well.

nlin.CD↗