Author name cluster

Qinghua Lu

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.

12 papers

1 author row

EAAI Journal 2026 Journal Article

An improved graph attention network for semantic segmentation of industrial point clouds in automotive battery sealing nail defect detection

Wei Pan
Yuhao Wu
Wenming Tang
Qinghua Lu
Yunzhi Zhang

Accurate defect detection in automotive battery sealing nails is vital for safety and reliability. Traditional methods combine two-dimensional (2D) vision for localization with three-dimensional (3D) vision for measurement, resulting in complex workflows and reduced efficiency. We propose Local Graph Attention for Semantic Segmentation (LGASS), an end-to-end 3D point cloud segmentation model. LGASS processes raw point cloud data from structured-light systems, performing simultaneous defect localization and geometric quantification in a single stage. By leveraging a graph attention mechanism in an encoder–decoder architecture, LGASS captures local geometric features and long-range dependencies, excelling on industrial metallic surfaces. Experiments show LGASS achieves 99. 47% Overall Accuracy (OA), 92. 37% mean Accuracy (mAcc), and 79. 23% mean Intersection over Union (mIoU), offering a robust solution for automated sealing nail inspection.

Details DOI

AAAI Conference 2026 Conference Paper

Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach

Yiyuan Yang
Guodong Long
Qinghua Lu
Liming Zhu
Jing Jiang

Federated foundation models represent a new paradigm to jointly fine-tune pre-trained foundation models across clients. It is still a challenge to fine-tune foundation models for a small group of new users or specialized scenarios, which typically involve limited data compared to the large-scale data used in pre-training. In this context, the trade-off between personalization and federation becomes more sensitive. To tackle these, we proposed a bi-level personalization framework for federated fine-tuning on foundation models. Specifically, we conduct personalized fine-tuning on the client-level using its private data, and then conduct a personalized aggregation on the server-level using similar users measured by client-specific task vectors. Given the personalization information gained from client-level fine-tuning, the server-level personalized aggregation can gain group-wise personalization information while mitigating the disturbance of irrelevant or interest-conflict clients with non-IID data. The effectiveness of the proposed algorithm has been demonstrated by extensive experimental analysis in benchmark datasets.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Federated Low-Rank Adaptation for Foundation Models: A Survey

Yiyuan Yang
Guodong Long
Qinghua Lu
Liming Zhu
Jing Jiang
Chengqi Zhang

Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework that enables multiple users to fine-tune these models while mitigating data privacy risks. Meanwhile, Low-Rank Adaptation (LoRA) offers a resource-efficient alternative for fine-tuning foundation models by dramatically reducing the number of trainable parameters. This survey examines how LoRA has been integrated into federated fine-tuning for foundation models—an area we term FedLoRA—by focusing on three key challenges: distributed learning, heterogeneity, and efficiency. We further categorize existing work based on the specific methods used to address each challenge. Finally, we discuss open research questions and highlight promising directions for future investigation, outlining the next steps for advancing FedLoRA.

PDF Details DOI

IS Journal 2023 Journal Article

Developing Responsible Chatbots for Financial Services: A Pattern-Oriented Responsible Artificial Intelligence Engineering Approach

Qinghua Lu
Yuxiu Luo
Liming Zhu
Mingjian Tang
Xiwei Xu
Jon Whittle

The recent release of ChatGPT has gained huge attention and discussion worldwide, with responsible artificial intelligence (RAI) being a crucial topic of discussion. One key question is, “How can we ensure that AI systems, like ChatGPT, are developed and adopted in a responsible way? ” To tackle RAI challenges, various ethical principles have been released by governments, organizations, and companies. However, those principles are very abstract and not practical enough. Further, significant efforts have been put on algorithm-level solutions that only address a narrow set of principles, such as fairness and privacy. To fill the gap, we adopt a pattern-oriented RAI engineering approach and build an RAI pattern catalog to operationalize RAI from a system perspective. In this article, we first summarize the major challenges in operationalizing RAI at scale and introduce how we use the RAI pattern catalog to address those challenges. We then examine the risks at each stage of the chatbot development process and recommend pattern-driven mitigations to evaluate the usefulness of the RAI pattern catalog in a real-world setting.

Details DOI

AAAI Conference 2023 Conference Paper

Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

Yue Tan
Yixin Liu
Guodong Long
Jing Jiang
Qinghua Lu
Chengqi Zhang

Graph neural networks (GNNs) have shown their superiority in modeling graph data. Owing to the advantages of federated learning, federated graph learning (FGL) enables clients to train strong GNN models in a distributed manner without sharing their private data. A core challenge in federated systems is the non-IID problem, which also widely exists in real-world graph data. For example, local data of clients may come from diverse datasets or even domains, e.g., social networks and molecules, increasing the difficulty for FGL methods to capture commonly shared knowledge and learn a generalized encoder. From real-world graph datasets, we observe that some structural properties are shared by various domains, presenting great potential for sharing structural knowledge in FGL. Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks. To explicitly extract the structure information rather than encoding them along with the node features, we define structure embeddings and encode them with an independent structure encoder. Then, the structure encoder is shared across clients while the feature-based knowledge is learned in a personalized way, making FedStar capable of capturing more structure-based domain-invariant information and avoiding feature misalignment issues. We perform extensive experiments over both cross-dataset and cross-domain non-IID FGL settings, demonstrating the superiority of FedStar.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Towards Self-Interpretable Graph-Level Anomaly Detection

Yixin Liu
Kaize Ding
Qinghua Lu
Fuyi Li
Leo Yu Zhang
Shirui Pan

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable dissimilarity compared to the majority in a collection. However, current works primarily focus on evaluating graph-level abnormality while failing to provide meaningful explanations for the predictions, which largely limits their reliability and application scope. In this paper, we investigate a new challenging problem, explainable GLAD, where the learning objective is to predict the abnormality of each graph sample with corresponding explanations, i. e. , the vital subgraph that leads to the predictions. To address this challenging problem, we propose a Self-Interpretable Graph aNomaly dETection model (SIGNET for short) that detects anomalous graphs as well as generates informative explanations simultaneously. Specifically, we first introduce the multi-view subgraph information bottleneck (MSIB) framework, serving as the design basis of our self-interpretable GLAD approach. This way SIGNET is able to not only measure the abnormality of each graph based on cross-view mutual information but also provide informative graph rationales by extracting bottleneck subgraphs from the input graph and its dual hypergraph in a self-supervised way. Extensive experiments on 16 datasets demonstrate the anomaly detection capability and self-interpretability of SIGNET.

PDF Details

AAAI Conference 2022 Conference Paper

FedProto: Federated Prototype Learning across Heterogeneous Clients

Yue Tan
Guodong Long
Lu Liu
Tianyi Zhou
Qinghua Lu
Jing Jiang
Chengqi Zhang

Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients’ knowledge occurs in the gradient space. For example, clients may differ in terms of data distribution, network latency, input/output space, and/or model architecture, which can easily lead to the misalignment of their local gradients. To improve the tolerance to heterogeneity, we propose a novel federated prototype learning (FedProto) framework in which the clients and server communicate the abstract class prototypes instead of the gradients. FedProto aggregates the local prototypes collected from different clients, and then sends the global prototypes back to all clients to regularize the training of local models. The training on each client aims to minimize the classification error on the local data while keeping the resulting local prototypes sufficiently close to the corresponding global ones. Moreover, we provide a theoretical analysis to the convergence rate of FedProto under non-convex objectives. In experiments, we propose a benchmark setting tailored for heterogeneous FL, with FedProto outperforming several recent FL approaches on multiple datasets.

PDF Details

EAAI Journal 2022 Journal Article

Learning invariant semantic representation for long-term robust visual localization

Junjun Wu
Qingwu Shi
Qinghua Lu
Xilin Liu
Xiaoman Zhu
Zeqin Lin

Long-term visual localization is a challenging problem in practice, which depends on the observed images captured by airborne camera to make the mobile robot perform the task of pose estimation during continuously navigating in complex scenes. Semantic information in the image has great invariance in changing environment and can be used to generate robust scene descriptor, but the performance of Convolutional Neural Network (CNN) based semantic segmentation highly depends on semantic labels, the generalization ability of the trained model is weak and labeling process for large-scale scene images is labor-intensive. To solve these problems, this paper proposes a new long-term visual localization method which fuses depth and semantic information in the scene, and its novelty lies in: (1) using a module of fusing depth and semantic information in the scene aims to extract the invariant scene representation when the environment changes, which effectively improves the robustness of long-term visual localization task and (2) using a domain adaptation module with the adversarial loss has adaptation ability from virtual dataset to real dataset, which require labor-free semantic labels annotation and generalize to more realistic application scenarios. Finally, the results show that our method outperforms state-of-the-art baselines under various challenging environments on the Extended CMU Seasons and RobotCar Seasons datasets in specific precision metrics.

Details DOI

EAAI Journal 2022 Journal Article

M-FasterSeg: An efficient semantic segmentation network based on neural architecture search

Junjun Wu
Huiyu Kuang
Qinghua Lu
Zeqin Lin
Qingwu Shi
Xilin Liu
Xiaoman Zhu

Image semantic segmentation is one of the key technologies for intelligent systems to understand natural scenes. As one of the important research directions in the field of visual intelligence, this technology has a wide range of application scenarios in the fields of mobile robots, drones, and intelligent driving. However, in practical applications, there may be problems such as inaccurate prediction of semantic labels, loss of segmented objects and background edge information. This paper proposes an improved semantic segmentation network that combines self-attention module and neural architecture search (NAS) method. The method first uses the NAS method to find a semantic segmentation network with multiple resolution branches. During the search process, the searched network structure is adjusted by combining the self-attention module, and then combined with the semantic segmentation networks searched by different branches to integrate into two semantic segmentation network models with different complexity, and finally integrate two network models with different complexity according to the current general teacher–student framework. The input image will first pass through the high complexity model to obtain more accurate parameters, which will affect the training weight of the student network, then pass the image into the low-complexity model to get the final predicted result. The experimental results on the Cityscapes dataset show that the accuracy of the algorithm is 69. 8 %, the inference speed is 166. 4 FPS, and the actual image segmentation speed is 48/s. It can optimize edge segmentation for better performance in complex scenes and achieve a good balance between real-time performance and accuracy in practical applications.

Details DOI

NeurIPS Conference 2021 Conference Paper

CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

Shuang Ao
Tianyi Zhou
Guodong Long
Qinghua Lu
Liming Zhu
Jing Jiang

Goal-conditioned reinforcement learning (RL) usually suffers from sparse reward and inefficient exploration in long-horizon tasks. Planning can find the shortest path to a distant goal that provides dense reward/guidance but is inaccurate without a precise environment model. We show that RL and planning can collaboratively learn from each other to overcome their own drawbacks. In ''CO-PILOT'', a learnable path-planner and an RL agent produce dense feedback to train each other on a curriculum of tree-structured sub-tasks. Firstly, the planner recursively decomposes a long-horizon task to a tree of sub-tasks in a top-down manner, whose layers construct coarse-to-fine sub-task sequences as plans to complete the original task. The planning policy is trained to minimize the RL agent's cost of completing the sequence in each layer from top to bottom layers, which gradually increases the sub-tasks and thus forms an easy-to-hard curriculum for the planner. Next, a bottom-up traversal of the tree trains the RL agent from easier sub-tasks with denser rewards on bottom layers to harder ones on top layers and collects its cost on each sub-task train the planner in the next episode. CO-PILOT repeats this mutual training for multiple episodes before switching to a new task, so the RL agent and planner are fully optimized to facilitate each other's training. We compare CO-PILOT with RL (SAC, HER, PPO), planning (RRT*, NEXT, SGT), and their combination (SoRB) on navigation and continuous control tasks. CO-PILOT significantly improves the success rate and sample efficiency.

PDF Details

NeurIPS Conference 2020 Conference Paper

Cooperative Heterogeneous Deep Reinforcement Learning

Han Zheng
Pengfei Wei
Jing Jiang
Guodong Long
Qinghua Lu
Chengqi Zhang

Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that classifies heterogeneous agents into two classes: global agents and local agents. Global agents are off-policy agents that can utilize experiences from the other agents. Local agents are either on-policy agents or population-based evolutionary algorithms (EAs) agents that can explore the local area effectively. We employ global agents, which are sample-efficient, to guide the learning of local agents so that local agents can benefit from the sample-efficient agents and simultaneously maintain their advantages, e. g. , stability. Global agents also benefit from effective local searches. Experimental studies on a range of continuous control tasks from the Mujoco benchmark show that CHDRL achieves better performance compared with state-of-the-art baselines.

PDF Details

AAAI Conference 2020 Conference Paper

Going Deep: Graph Convolutional Ladder-Shape Networks

Ruiqi Hu
Shirui Pan
Guodong Long
Qinghua Lu
Liming Zhu
Jing Jiang

Neighborhood aggregation algorithms like spectral graph convolutional networks (GCNs) formulate graph convolutions as a symmetric Laplacian smoothing operation to aggregate the feature information of one node with that of its neighbors. While they have achieved great success in semisupervised node classiﬁcation on graphs, current approaches suffer from the over-smoothing problem when the depth of the neural networks increases, which always leads to a noticeable degradation of performance. To solve this problem, we present graph convolutional ladder-shape networks (GCLN), a novel graph neural network architecture that transmits messages from shallow layers to deeper layers to overcome the over-smoothing problem and dramatically extend the scale of the neural networks with improved performance. We have validated the effectiveness of proposed GCLN at a node-wise level with a semi-supervised task (node classiﬁcation) and an unsupervised task (node clustering), and at a graph-wise level with graph classiﬁcation by applying a differentiable pooling operation. The proposed GCLN outperforms original GCNs, deep GCNs and other state-of-the-art GCN-based models for all three tasks, which were designed from various perspectives on six real-world benchmark data sets.

PDF Details