Author name cluster

Chen Qiu

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.

9 papers

2 author rows

UAI Conference 2025 Conference Paper

Enhanced Equilibria-Solving via Private Information Pre-Branch Structure in Adversarial Team Games

Chen Qiu
Haobo Fu
Kai Li
Jiajia Zhang
Xuan Wang

In ex ante coordinated adversarial team games (ATGs), a team competes against an adversary, and team members can only coordinate their strategies before the game starts. The team-maxmin equilibrium with correlation (TMECor) is a suitable solution concept for extensive-form sequential ATGs. One class of TMECor-solving methods transforms the problem into solving NE in two-player zero-sum games, leveraging well-established tools for the latter. However, existing methods are fundamentally action-based, resulting in poor generalizability and low solving efficiency due to the exponential growth in the size of the transformed game. To address the above issues, we propose an efficient game transformation method based on private information, where all team members are represented by a single coordinator. We designed a structure called private information pre-branch, which makes decisions considering all possible private information from teammates. We prove that the size of the game transformed by our method is exponentially reduced compared to the current state-of-the-art. Moreover, we demonstrate equilibria equivalence. Experimentally, our method achieves a significant speedup of 182. 89$\times$ to 694. 44$\times$ in scenarios where the current state-of-the-art method can work, such as small-scale Kuhn poker and Leduc poker. Furthermore, our method is applicable to larger games and those with dynamically changing private information, such as Goofspiel.

Details

EAAI Journal 2025 Journal Article

Optimizing strategy selection in hidden role games

Yingying Xu
Chen Qiu
Jinheng Xiao
Jiajia Zhang
Shuhan Qi
Xuan Wang

We address hidden-role decision making under uncertainty in The Resistance: Avalon. We present DeepBayes, which augments a standard Counterfactual Regret Minimization Plus (CFR+) decision procedure with two complementary inference components. First, a history-driven role assignment prediction network generates role-assignment hypotheses from past gameplay, which are used to improve the estimation of Counterfactual Values (CFVs). Second, a Bayesian Identity Recognition (BIR) method produces explicit posterior beliefs about opposing identities online as play unfolds. During CFR+ iterations, the algorithm selects actions by jointly considering the CFVs estimated under the generated role assignments and the posterior beliefs from BIR. In five-player Avalon experiments, DeepBayes achieves consistent gains in win rate over strong baselines.

Details DOI

TMLR Journal 2025 Journal Article

Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior

Lorenzo Perini
Maja Rudolph
Sabrina Schmedding
Chen Qiu

Anomaly detection is the task of identifying examples that do not behave as expected. Because anomalies are rare and unexpected events, collecting real anomalous examples is often challenging in several applications. In addition, learning an anomaly detector with limited (or no) anomalies often yields poor prediction performance. One option is to employ auxiliary synthetic anomalies to improve the model training. However, synthetic anomalies may be of poor quality: anomalies that are unrealistic or indistinguishable from normal samples may deteriorate the detector's performance. Unfortunately, no existing methods quantify the quality of auxiliary anomalies. We fill in this gap and propose the expected anomaly posterior (EAP), an uncertainty-based score function that measures the quality of auxiliary anomalies by quantifying the total uncertainty of an anomaly detector. Experimentally on 40 benchmark datasets of images and tabular data, we show that EAP outperforms 12 adapted data quality estimators in the majority of cases. Code of EAP is available at: https://github.com/Lorenzo-Perini/ExpectedAnomalyPosterior.

PDF Details

ICLR Conference 2024 Conference Paper

Federated Text-driven Prompt Generation for Vision-Language Models

Chen Qiu
Xingyu Li
Chaithanya Kumar Mummadi
Madan Ravi Ganesh
Zhenzhen Li
Lu Peng 0001
Wan-Yi Lin

Prompt learning for vision-language models, e.g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons. Existing prompt learning techniques replace hand-crafted text prompts with learned vectors that offer improvements on seen classes, but struggle to generalize to unseen classes. Our work addresses this challenge by proposing Federated Text-driven Prompt Generation (FedTPG), which learns a unified prompt generation network across multiple remote clients in a scalable manner. The prompt generation network is conditioned on task-related text input, thus is context-aware, making it suitable to generalize for both seen and unseen classes. Our comprehensive empirical evaluations on nine diverse image classification datasets show that our method is superior to existing federated prompt learning methods, achieving better overall generalization on both seen and unseen classes, as well as datasets.

Details

NeurIPS Conference 2023 Conference Paper

Zero-Shot Anomaly Detection via Batch Normalization

Aodong Li
Chen Qiu
Marius Kloft
Padhraic Smyth
Maja Rudolph
Stephan Mandt

Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the "new normal, " has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch normalization, enabling automatic zero-shot generalization for unseen AD tasks. This simple recipe, batch normalization plus meta-training, is a highly effective and versatile tool. Our results demonstrate the first zero-shot AD results for tabular data and outperform existing methods in zero-shot anomaly detection and segmentation on image data from specialized domains.

PDF Details

IROS Conference 2022 Conference Paper

Enabling Massage Actions: An Interactive Parallel Robot with Compliant Joints

Huixu Dong
Yue Feng
Chen Qiu
Ye Pan
Miao He
I-Ming Chen 0001

We propose a parallel massage robot with compliant joints based on the series elastic actuator (SEA), offering a unified force-position control approach. First, the kinematic and static force models are established for obtaining the corresponding control variables. Then, a novel force-position control strategy is proposed to separately control the force-position along the normal direction of the surface and another two-direction displacement, without the requirement of a robotic dynamics model. To evaluate its performance, we implement a series of robotic massage experiments. The results demonstrate that the proposed massage manipulator can successfully achieve desired forces and motion patterns of massage tasks, arriving at a high-score user experience.

Details

ICRA Conference 2022 Conference Paper

Learning-based Ellipse Detection for Robotic Grasps of Cylinders and Ellipsoids

Huixu Dong
Jiadong Zhou
Chen Qiu
Dilip K. Prasad
I-Ming Chen 0001

In our daily life, there are many objects represented by cylindrical shapes and ellipsoids. The tops of these objects are formed by elliptic shape primitives. Thus, it is available for a robot to manipulate these objects by ellipse detection. In this work, we propose a novel approach to generating ground truth for training the model based on domain randomization. Using synthetic data generated in this manner, we build an end-to-end deep neural network with a detection backbone and then, combine multiple branches archived from the backbone for sharing the multiple-scale features; further, after employing active rotation filters, the features pass through the region proposal net to form the prediction branches of the box, orientation regression, and object classification; finally, these branches are fused to do ellipse detection, allowing robotic manipulations of cylinders and ellipsoids. To demonstrate the capabilities of the proposed detector, we show the comparison results with the state-of-the-art detector on synthetic and public datasets. The proposed model for ellipse detection and data generation pipeline based on domain randomization in a simulation are evaluated by a series of robotic manipulations implemented in real application scenarios. The results illustrate a high success rate on real-world grasp attempts despite having only been trained on a synthetic dataset. (A video of some robotic experiments is available on YouTube: https://youtu.be/Ueg1XSI2S98).

Details

IJCAI Conference 2022 Conference Paper

Raising the Bar in Graph-level Anomaly Detection

Chen Qiu
Marius Kloft
Stephan Mandt
Maja Rudolph

Graph-level anomaly detection has become a critical topic in diverse areas, such as financial fraud detection and detecting anomalous activities in social networks. While most research has focused on anomaly detection for visual data such as images, where high detection accuracies have been obtained, existing deep learning approaches for graphs currently show considerably worse performance. This paper raises the bar on graph-level anomaly detection, i. e. , the task of detecting abnormal graphs in a set of graphs. By drawing on ideas from self-supervised learning and transformation learning, we present a new deep learning approach that significantly improves existing deep one-class approaches by fixing some of their known problems, including hypersphere collapse and performance flip. Experiments on nine real-world data sets involving nine techniques reveal that our method achieves an average performance improvement of 11. 8% AUC compared to the best existing approach.

PDF Details DOI

IROS Conference 2014 Conference Paper

A novel continuum-style robot with multilayer compliant modules

Peng Qi 0001
Chen Qiu
Hongbin Liu 0001
Jian S. Dai 0001
Lakmal D. Seneviratne
Kaspar Althoefer

This paper introduces a novel continuum-style robot that integrates multiple layers of compliant modules. Its essential features lie in that its bending is not based on natural compliance of a continuous backbone element or soft skeletal elements but instead is based on the compliance of each structured planar module. This structure provides several important advantages. First, it demonstrates a large linear bending motion, whilst avoiding joint friction. Second, its contraction and bending motion are decoupled. Third, it possesses ideal back-drivability and a low hysteresis. We further provide an analytical method to study the compliance characteristics of the planar module and derive the statics and kinematics of the robot. The paper provides an overview of experiments validating the design and analysis.

Details