Author name cluster

Wen Dong

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

NeurIPS Conference 2025 Conference Paper

Certifying Deep Network Risks and Individual Predictions with PAC-Bayes Loss via Localized Priors

Wen Dong

As machine learning increasingly relies on large, opaque foundation models powering generative and agentic AI, deploying these systems in safety-critical settings demands rigorous guarantees on their generalization beyond training data. PAC-Bayes theory offers principled certificates linking training performance to generalization risk, yet existing approaches are rarely practical: simple theoretical priors yield vacuous bounds, while data-dependent priors trained separately are computationally costly or introduce bias. To bridge this fundamental gap, we propose a localized PAC-Bayes prior—a structured, computationally efficient prior softly concentrated near parameters favored during standard training, enabling effective exploration without costly data splits. By integrating this localized prior directly into standard training loss, we produce practically tight generalization certificates without workflow disruption. Theoretically, under standard neural tangent kernel assumptions, our bound shrinks as networks widen and datasets grow, becoming negligible in practical regimes. Empirically, we certify generalization across image classification, NLP fine-tuning, and semantic segmentation, typically within three percentage points of test errors at ImageNet scale, while providing rigorous guarantees for individual predictions, selective rejection, and robustness.

PDF Details

ECAI Conference 2025 Conference Paper

Region-Aware Compositional Context Prompting for Zero-Shot Anomaly Detection

Wen Dong
Guanglei Chu
Zhe Pan
Guo-Sen Xie
Caifeng Shan
Fang Zhao 0006

Zero-shot anomaly detection (ZSAD) aims to identify anomalies of unseen classes without requiring samples from those classes. Existing methods typically rely on pre-trained visual language models, such as CLIP, to detect anomalies by designing or learning generic text prompts and computing similarities with image features, which often fail to address the complexity and novelty of anomaly patterns, especially when the target domain exhibits significant differences from the source domain. To address the problems, we propose Region-aware Compositional Context Prompting (ReCo-CoP) for ZSAD, which dynamically generates contextual prompts by integrating both global and local visual information. Specifically, we introduce a Compositional Context Prompting (CCP) module that incorporates global visual features into the context through a set of basis vectors shared among images, and a Regional Context Prompting (RCP) module that optimizes the context based on image patch features, thereby enhancing the model’s ability to perceive local abnormal regions. Additionally, we combine dynamically generated prompts with static generic prompts to prevent the model from losing the essential general knowledge. Extensive experiments on 12 datasets from industrial and medical domains demonstrate the superior zero-shot detection performance of our model. The code is available at https: //github. com/WenDongyp/ReCoCoP

Details

AAMAS Conference 2025 Conference Paper

Simulating and Evaluating Generative Modeling and Collaborative Filtering in Complex Social Networks

Wen Dong
Fairul Mohd-Zaid

We introduce a multi-agent simulation framework for modeling large-scale online social dynamics by combining retrieval-augmented large language models, generative embedding methods, and collaborative filtering. Our approach learns diverse agent embeddings to capture varying user behaviors and employs a multi-layer perceptron for user-content ranking. We compare three strategies—(1) a generative modeling approach that integrates agent embeddings and collaborative filtering, (2) an LLM-based method grounded in historical context, and (3) a reflection-based clustering technique—and evaluate them on metrics such as comment volume, tree depth, user engagement patterns, and topic distribution. Results show that generative embeddings coupled with collaborative filtering better approximate complex phenomena like localized influencers, specialized subcommunities, and emergent echo chambers. Moreover, our framework supports policy-driven experimentation by incorporating social regularizers (cohesion, polarization, and bias) to simulate scenarios ranging from tightly knit communities to more balanced, cross-cutting interactions. By integrating largescale data with adaptable LLM-driven agents, this work provides a versatile, data-centric foundation for simulating and analyzing online social ecosystems at scale.

PDF

AAAI Conference 2024 Conference Paper

Exploiting Polarized Material Cues for Robust Car Detection

Wen Dong
Haiyang Mei
Ziqi Wei
Ao Jin
Sen Qiu
Qiang Zhang
Xin Yang

Car detection is an important task that serves as a crucial prerequisite for many automated driving functions. The large variations in lighting/weather conditions and vehicle densities of the scenes pose significant challenges to existing car detection algorithms to meet the highly accurate perception demand for safety, due to the unstable/limited color information, which impedes the extraction of meaningful/discriminative features of cars. In this work, we present a novel learning-based car detection method that leverages trichromatic linear polarization as an additional cue to disambiguate such challenging cases. A key observation is that polarization, characteristic of the light wave, can robustly describe intrinsic physical properties of the scene objects in various imaging conditions and is strongly linked to the nature of materials for cars (e.g., metal and glass) and their surrounding environment (e.g., soil and trees), thereby providing reliable and discriminative features for robust car detection in challenging scenes. To exploit polarization cues, we first construct a pixel-aligned RGB-Polarization car detection dataset, which we subsequently employ to train a novel multimodal fusion network. Our car detection network dynamically integrates RGB and polarization features in a request-and-complement manner and can explore the intrinsic material properties of cars across all learning samples. We extensively validate our method and demonstrate that it outperforms state-of-the-art detection methods. Experimental results show that polarization is a powerful cue for car detection. Our code is available at https://github.com/wind1117/AAAI24-PCDNet.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Bayesian Multi-type Mean Field Multi-agent Imitation Learning

Fan Yang
Alina Vereshchaka
Changyou Chen
Wen Dong

Multi-agent Imitation learning (MAIL) refers to the problem that agents learn to perform a task interactively in a multi-agent system through observing and mimicking expert demonstrations, without any knowledge of a reward function from the environment. MAIL has received a lot of attention due to promising results achieved on synthesized tasks, with the potential to be applied to complex real-world multi-agent tasks. Key challenges for MAIL include sample efficiency and scalability. In this paper, we proposed Bayesian multi-type mean field multi-agent imitation learning (BM3IL). Our method improves sample efficiency through establishing a Bayesian formulation for MAIL, and enhances scalability through introducing a new multi-type mean field approximation. We demonstrate the performance of our algorithm through benchmarking with three state-of-the-art multi-agent imitation learning algorithms on several tasks, including solving a multi-agent traffic optimization problem in a real-world transportation network. Experimental results indicate that our algorithm significantly outperforms all other algorithms in all scenarios.

PDF Details

AAAI Conference 2020 Conference Paper

Variational Adversarial Kernel Learned Imitation Learning

Fan Yang
Alina Vereshchaka
Yufan Zhou
Changyou Chen
Wen Dong

Imitation learning refers to the problem where an agent learns to perform a task through observing and mimicking expert demonstrations, without knowledge of the cost function. Stateof-the-art imitation learning algorithms reduce imitation learning to distribution-matching problems by minimizing some distance measures. However, the distance measure may not always provide informative signals for a policy update. To this end, we propose the variational adversarial kernel learned imitation learning (VAKLIL), which measures the distance using the maximum mean discrepancy with variational kernel learning. Our method optimizes over a large cost-function space and is sample efﬁcient and robust to overﬁtting. We demonstrate the performance of our algorithm through benchmarking with four state-of-the-art imitation learning algorithms over ﬁve high-dimensional control tasks, and a complex transportation control task. Experimental results indicate that our algorithm signiﬁcantly outperforms related algorithms in all scenarios.

PDF Details

AAMAS Conference 2019 Conference Paper

Optimal Control of Complex Systems through Variational Inference with a Discrete Event Decision Process

Fan Yang
Bo Liu
Wen Dong

Complex social systems are composed of interconnected individuals whose interactions result in group behaviors. Optimal control of a real-world complex system has many applications, including road traffic management, epidemic prevention, and information dissemination. However, such real-world complex system control is difficult to achieve because of high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decision maker. Prior methods can be divided into two categories: simulation-based and analytical approaches. Existing simulation approaches have high-variance in Monte Carlo integration, and the analytical approaches suffer from modeling inaccuracy. We adopted simulation modeling in specifying the complex dynamics of a complex system, and developed analytical solutions for searching optimal strategies in a complex network with high-dimensional state-action space. To capture the complex system dynamics, we formulate the complex social network decision making problem as a discrete event decision process. To address the curse of dimensionality and search in high-dimensional state action spaces in complex systems, we reduce control of a complex system to variational inference and parameter learning, introduce Bethe entropy approximation, and develop an expectation propagation algorithm. Our proposed algorithm leads to higher system expected rewards, faster convergence, and lower variance of value function in a realworld transportation scenario than state-of-the-art analytical and sampling approaches.

PDF

NeurIPS Conference 2017 Conference Paper

Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems

Le Fang
Fan Yang
Wen Dong
Tong Guan
Chunming Qiao

Technological breakthroughs allow us to collect data with increasing spatio-temporal resolution from complex interaction systems. The combination of high-resolution observations, expressive dynamic models, and efficient machine learning algorithms can lead to crucial insights into complex interaction dynamics and the functions of these systems. In this paper, we formulate the dynamics of a complex interacting network as a stochastic process driven by a sequence of events, and develop expectation propagation algorithms to make inferences from noisy observations. To avoid getting stuck at a local optimum, we formulate the problem of minimizing Bethe free energy as a constrained primal problem and take advantage of the concavity of dual problem in the feasible domain of dual variables guaranteed by duality theorem. Our expectation propagation algorithms demonstrate better performance in inferring the interaction dynamics in complex transportation networks than competing models such as particle filter, extended Kalman filter, and deep neural networks.

PDF Details

NeurIPS Conference 2016 Conference Paper

Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model

Zhen Xu
Wen Dong
Sargur Srihari

Social dynamics is concerned primarily with interactions among individuals and the resulting group behaviors, modeling the temporal evolution of social systems via the interactions of individuals within these systems. In particular, the availability of large-scale data from social networks and sensor networks offers an unprecedented opportunity to predict state-changing events at the individual level. Examples of such events include disease transmission, opinion transition in elections, and rumor propagation. Unlike previous research focusing on the collective effects of social systems, this study makes efficient inferences at the individual level. In order to cope with dynamic interactions among a large number of individuals, we introduce the stochastic kinetic model to capture adaptive transition probabilities and propose an efficient variational inference algorithm the complexity of which grows linearly — rather than exponentially— with the number of individuals. To validate this method, we have performed epidemic-dynamics experiments on wireless sensor network data collected from more than ten thousand people over three years. The proposed algorithm was used to track disease transmission and predict the probability of infection for each individual. Our results demonstrate that this method is more efficient than sampling while nonetheless achieving high accuracy.

PDF Details

AAMAS Conference 2016 Conference Paper

Variational Inference with Agent-Based Models

Wen Dong

In this paper, we develop a variational method to track and make predictions about a real-world system from continuous imperfect observations about this system, using an agent-based model that describes the system dynamics. By combining the power of big data with the power of modelthinking in the stochastic process framework, we can make many valuable predictions. We show how to track the spread of an epidemic at the individual level and how to make shortterm predictions about traffic congestion. This method points to a new way to bring together modelers and data miners by turning the real world into a living lab.

PDF