Zhen Wang’s research while affiliated with Northwestern University and other places

This paper introduces a novel memristive FitzHugh–Rinzel neural oscillator and investigates its chaotic dynamics using bifurcation diagrams and Lyapunov exponents. A neural network based on this oscillator is constructed to study synchronization control under a non-local coupling structure, considering electrical, chemical, and electrochemical coupling. The results show that synchronization occurs at weaker coupling strengths under chemical coupling than electrical coupling, with a non-monotonic decrease in synchronization error as the coupling strength increases. However, at high chemical and electrochemical coupling strengths, the system undergoes oscillation death, where neurons cease oscillating and reach a stable state. These findings highlight the distinct roles of chemical and electrochemical interactions in shaping neural network synchronization and collective dynamics.

The tragedy of the commons, where individual self-interest leads to collectively disastrous outcomes, is a pervasive challenge in human society. Recent studies have demonstrated that similar phenomena can arise in generative multi-agent systems (MASs). To address this challenge, this paper explores the use of reputation systems as a remedy. We propose RepuNet, a dynamic, dual-level reputation framework that models both agent-level reputation dynamics and system-level network evolution. Specifically, driven by direct interactions and indirect gossip, agents form reputations for both themselves and their peers, and decide whether to connect or disconnect other agents for future interactions. Through two distinct scenarios, we show that RepuNet effectively mitigates the 'tragedy of the commons', promoting and sustaining cooperation in generative MASs. Moreover, we find that reputation systems can give rise to rich emergent behaviors in generative MASs, such as the formation of cooperative clusters, the social isolation of exploitative agents, and the preference for sharing positive gossip rather than negative ones.

Fact verification task has emerged as an essential research topic recently due to abundant fake news spreading on the Internet. The task based on unstructured data (i.e., news) has achieved great development, but the task based on structured data (i.e., table) is still in the primary development period. The existing methods usually construct complete heterogeneous graph networks around statement, table, and program subgraphs, and then infer to learn similar semantics on them for fact verification. However, they generally connect the nodes with the same content between subgraphs directly to frame a larger graph network, which has serious sparsity in connections, especially when subgraphs possess limited semantics. To this end, we propose tight-fitting graph inference network (TFGIN), which innovatively builds tight-fitting graphs (TF-graph) to strengthen the connections of subgraphs, and designs inference modeling layer (IML) to learn coherence evidence for fact verification. Specifically, different from traditional connection ways, the constructed TF-graph enhances inter-graph and intra-graph connections of subgraphs through subgraph segmentation and interaction guidance mechanisms. Inference modeling layer could reason the semantics with strong correlation and high consistency as explainable evidence. Experiments on three competitive datasets confirm the superiority and scalability of our TFGIN.

With the advancement of artificial intelligence, human interest in human-agent collaboration has grown, raising a series of challenges regarding the relationship between agents and humans, such as trust and cooperation. This leads to the inevitable consideration of the inherent human traits of subjective interaction preferences for different groups, particularly in human-agent hybrid systems where human-human, agent-agent, and human-agent interactions coexist. However, understanding how individual interaction preferences influence cooperation within such systems remains a major challenge. To address this, this study proposes a human-agent hybrid prisoner’s dilemma game system within the framework of evolutionary game theory. In spatial networks, the primary distinction between agents and humans lies in their decision-making flexibility: humans possess higher adaptive capabilities, follow link dynamics, and employ free decision-making rules, which allows them to select different strategies for different neighbors. In contrast, agents follow node dynamics, applying uniform decision rules and using the same strategy across all neighbors. We define subjective preferences for individuals in various groups, including interaction preferences between homogeneous and heterogeneous groups. The simulation results demonstrate that both humans and agents display asymmetric interaction preferences toward groups with different identities, which significantly enhances cooperative behavior in the system. In the hybrid system, human groups exhibit more stable prosocial behavior, whereas agent groups form highly cooperative clusters when there is a strong interaction preference for human groups. Additionally, endowing agents with the ability to identify their opponents effectively mitigates the interaction dilemma among agents.

Quantum nonlocality describes a stronger form of quantum correlation than that of entanglement. It refutes Einstein’s belief of local realism and is among the most distinctive and enigmatic features of quantum mechanics. It is a crucial resource for achieving quantum advantages in a variety of practical applications, ranging from cryptography and certified random number generation via self-testing to machine learning. Nevertheless, the detection of nonlocality, especially in quantum many-body systems, is notoriously challenging. Here, we report an experimental certification of genuine multipartite Bell-operator correlations, which signal nonlocality in quantum many-body systems, up to 24 qubits with a fully programmable superconducting quantum processor. In particular, we employ energy as a Bell-operator correlation witness and variationally decrease the energy of a many-body system across a hierarchy of thresholds, below which an increasing Bell-operator correlation depth can be certified from experimental data. We variationally prepare the low-energy state of a two-dimensional honeycomb model with 73 qubits and certify its Bell-operator correlations by measuring an energy that surpasses the corresponding classical bound with up to 48 standard deviations. In addition, we variationally prepare a sequence of low-energy states and certify their genuine multipartite Bell-operator correlations up to 24 qubits via energies measured efficiently by parity oscillation and multiple quantum coherence techniques. Our results establish a viable approach for preparing and certifying multipartite Bell-operator correlations, which provide not only a finer benchmark beyond entanglement for quantum devices, but also a valuable guide toward exploiting multipartite Bell correlations in a wide spectrum of practical applications. Published by the American Physical Society 2025

Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence. In reinforcement learning, rationally reusing the policies acquired from other tasks or human experts is critical for tackling problems that are difficult to learn from scratch. In this work, we present a framework called Selective Myopic bEhavior Control (SMEC), which results from the insight that the short-term behaviors of prior policies are sharable across tasks. By evaluating the behaviors of prior policies via a hybrid value function architecture, SMEC adaptively aggregates the sharable short-term behaviors of prior policies and the long-term behaviors of the task policy, leading to coordinated decisions. Empirical results on a collection of manipulation and locomotion tasks demonstrate that SMEC outperforms existing methods, and validate the ability of SMEC to leverage related prior policies.

In this study, we present a deterministic convergence analysis of Gated Recurrent Unit (GRU) networks enhanced by a smoothing L1 regularization technique. While GRU architectures effectively mitigate gradient vanishing/exploding issues in sequential modeling, they remain prone to overfitting, particularly under noisy or limited training data. Traditional L1 regularization, despite enforcing sparsity and accelerating optimization, introduces non-differentiable points in the error function, leading to oscillations during training. To address this, we propose a novel smoothing L1 regularization framework that replaces the non-differentiable absolute function with a quadratic approximation, ensuring gradient continuity and stabilizing the optimization landscape. Theoretically, we rigorously establish three key properties of the resulting smoothing L1-regularized GRU (SL1-GRU) model: (1) monotonic decrease of the error function across iterations, (2) weak convergence characterized by vanishing gradients as iterations approach infinity, and (3) strong convergence of network weights to fixed points under finite conditions. Comprehensive experiments on benchmark datasets-spanning function approximation, classification (KDD Cup 1999 Data, MNIST), and regression tasks (Boston Housing, Energy Efficiency)-demonstrate SL1-GRUs superiority over baseline models (RNN, LSTM, GRU, L1-GRU, L2-GRU). Empirical results reveal that SL1-GRU achieves 1.0%–2.4% higher test accuracy in classification, 7.8%–15.4% lower mean squared error in regression compared to unregularized GRU, while reducing training time by 8.7%–20.1%. These outcomes validate the method’s efficacy in balancing computational efficiency and generalization capability, and they strongly corroborate the theoretical calculations. The proposed framework not only resolves the non-differentiability challenge of L1 regularization but also provides a theoretical foundation for convergence guarantees in recurrent neural network training.

Reciprocity plays a crucial role in maintaining cooperation in human societies and AI systems. In this paper, we focus on reciprocity within multichannel games and examine how cooperation evolves in this context. We propose a unified framework that allows us to evaluate the reputations of interdependent actions across multiple channels while simultaneously exploring both direct and indirect reciprocity mechanisms. We identify partner and semi-partner strategies under both forms of reciprocity, with the former leading to full cooperation and the latter resulting in partial cooperation. Through equilibrium analysis, we characterize the conditions under which full cooperation and partial cooperation emerge. Moreover, we show that when players can link multiple interactions, they learn to coordinate their behavior across different games to maximize overall cooperation. Our findings provide new insights into the maintenance of cooperation across various reciprocity mechanisms and interaction patterns.

With the diversification of online social platforms, news dissemination has become increasingly complex, heterogeneous, and multimodal, making the fake news detection task more challenging and crucial. Previous works mainly focus on obtaining social relationships of news via retweets, limiting the accurate detection when real cascades are inaccessible. Given the proven assessment of the spreading influence of events, this paper proposes a method called HML (Complex Heterogeneous Multimodal Fake News Detection method via Latent Network Inference). Specifically, an improved social latent network inference strategy is designed to estimate the maximum likelihood of news influences under the same event. Meanwhile, a novel heterogeneous graph is built based on social attributes for multimodal news under different events. Further, to better aggregate the relationships among heterogeneous multimodal features, this paper proposes a self-supervised-based multimodal content learning strategy, to enhance, align, fuse and compare heterogeneous modal contents. Based above, a personalized heterogeneous graph representation learning is designed to classify fake news. Extensive experiments demonstrate that the proposed method outperforms the SOTA in real social media news datasets.