Author name cluster

Kai Guo

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

AAAI Conference 2026 Conference Paper

Revealing the Invisible: Latent Structure Modeling for Semantically Consistent Cloud Removal

Jingwei Xin
Kai Guo
Jie Li
Nannan Wang

Cloud removal (CR) in remote sensing imagery is a critical yet challenging task due to complex cloud patterns and diverse underlying ground structures. Despite recent progress in generative models such as diffusion models, CR remains limited by their inadequate capability to perceive and reconstruct structured information beneath cloud-covered areas. In this work, we propose a Visibility-guided Semantic Estimation and Reconstruction network for cloud removal (VISER-CR), which reformulates CR as a structure-guided completion problem. Specifically, VISER-CR explicitly models cloud interference via spatial masking, encouraging the model to reason beyond pixel-level appearance and enhance scene-level structural understanding. Moreover, to further improve the representation of structural information, we introduce Patch Saliency Encoding, a self-guided mechanism that implicitly models structural alignment among patches, significantly enhancing clustering consistency and semantic separability in the latent space. This adaptive mechanism guides the network to focus on learning and reconstructing structurally important regions, thereby reducing redundancy and improving overall cloud removal performance. Extensive experiments on multiple benchmark datasets demonstrate the superior effectiveness of our method.

PDF Details DOI

EAAI Journal 2025 Journal Article

Classification model for blast furnace status based on multi-source information

Kai Guo
YaXian Zhang
Sen Zhang
WenDong Xiao

The blast furnace (BF) is the key equipment for smelting, which has a significant impact on the sustainable development of global environment and energy. Therefore, it will be helpful for the operators if accurate evaluation to the status of the BF is realized. The classification model based on multi-source information is proposed in this paper, where the kernel fisher (KF) algorithm is enhanced to simplify the complexity both in algorithm and data dimensionality. The proposed model can realize the classification of both the distribution of gas flow (GF) and the geometric information of the burden surface (BS), and this paper also proposes a dynamic process adaptive kernel fisher (DPAKF) algorithm to enhance the adaptive ability of the classifier, where the online algorithm updating mechanism is designed. The experimental results demonstrate that the classification accuracy was increased from 90% to 95%, and the time expense of DPAKF was 236 s, which is prior compared with the existing support vector machine (SVM), k-nearest neighbor (KNN) and genetic algorithm (GA) models. The results of the student's t-distribution show that the statistics between DPAKF and KF, SVM, KNN and GA were 1. 25, 2. 81, 2. 84 and 2. 96, respectively, which demonstrate that there are significant statistical differences between DPAKF and SVM, KNN, and GA. This research provides a potential solution to the classification problem of the BF.

Details DOI

IJCAI Conference 2025 Conference Paper

Disentangling Multi-view Representations via Curriculum Learning with Learnable Prior

Kai Guo
Jiedong Wang
Xi Peng
Peng Hu
Hao Wang

Multi-view representation learning methods typically follow a consistent-and-specific pipeline that aims at extracting latent representations for an entity from its multiple observable views to facilitate downstream tasks. However, most of them overlook the complex underlying correlation between different views. To solve this issue, we delve into a well-known property of neural networks (NNs) that NNs tend to learn simple patterns first and then hard ones. In our case, view-consistent representations are simple patterns and view-specific representations are hard. To this end, we propose to disentangle view-consistency and view-specificity and learn them gradually. Specifically, we devise a novel curriculum learning approach that adjusts the whole model to learn view-consistent representations first and then progressively view-specific representations. Besides, we saddle each view with a learnable prior that allows each view-specific representation to appropriate its distribution. Moreover, we incorporate a mixture-of-experts layer and a disentangling module to further enhance the quality of the learned representations. Extensive experiments on five real-world datasets show that the proposed model outperforms its counterparts markedly. The code is available at https: //github. com/XLearning-SCU/2025-IJCAI-CL2P.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

Xinnan Dai
Kai Yang
Jay Revolinsky
Kai Guo
Aoran Wang
Bohang Zhang
Jiliang Tang

Recent studies suggest that large language models (LLMs) possess the capability to solve graph reasoning tasks. Notably, even when graph structures are embedded within textual descriptions, LLMs can still effectively answer related questions. This raises a fundamental question: How can a decoder-only Transformer architecture understand underlying graph structures? To address this, we start with the substructure extraction task, interpreting the inner mechanisms inside the transformers and analyzing the impact of the input queries. Specifically, through both empirical results and theoretical analysis, we present Induced Substructure Filtration (ISF), a perspective that captures the substructure identification in the multi-layer transformers. We further validate the ISF process in LLMs, revealing consistent internal dynamics across layers. Building on these insights, we explore the broader capabilities of Transformers in handling diverse graph types. Specifically, we introduce the concept of thinking in substructures to efficiently extract complex composite patterns, and demonstrate that decoder-only Transformers can successfully extract substructures from attributed graphs, such as molecular graphs. Together, our findings offer a new insight on how sequence-based Transformers perform the substructure extraction task over graph data.

PDF Details

IJCAI Conference 2025 Conference Paper

Learning Robust Multi-view Representation Using Dual-masked VAEs

Jiedong Wang
Kai Guo
Peng Hu
Xi Peng
Hao Wang

Most existing multi-view representation learning methods assume view-completeness and noise-free data. However, such assumptions are strong in real-world applications. Despite advances in methods tailored to view-missing or noise problems individually, a one-size-fits-all approach that concurrently addresses both remains unavailable. To this end, we propose a holistic method, called Dual-masked Variational Autoencoders (DualVAE), which aims at learning robust multi-view representation. The DualVAE exhibits an innovative amalgamation of dual-masked prediction, mixture-of-experts learning, representation disentangling, and a joint loss function in wrapping up all components. The key novelty lies in the dual-masked (view-mask and patch-mask) mechanism to mimic missing views and noisy data. Extensive experiments on four multi-view datasets show the effectiveness of the proposed method and its superior performance in comparison to baselines. The code is available at https: //github. com/XLearning-SCU/2025-IJCAI-DualVAE.

PDF Details DOI

EAAI Journal 2024 Journal Article

Adaptive feature fusion and disturbance correction for accurate remaining useful life prediction of rolling bearings

Kai Guo
Jun Ma
Jiande Wu
Xin Xiong

As a key component in the transmission system of high-speed trains, bearings need to withstand certain loads while rotating at high speeds. Once a failure occurs, it can directly affect the safety of train operations. Therefore, it is of great significance to establish a reliable remaining useful life model to ensure train operation safety. Addressing the problems of redundant features in the existing multi-feature fusion process, which affects diagnostic performance, and the spurious fluctuations in the fusion features, which cause inaccurate determination of the start fault time and lead to low prediction accuracy of remaining useful life, we propose a method based on adaptive feature fusion and the autoregressive integrated moving average model for rolling bearing prediction. Firstly, features from the time domain, frequency domain, and entropy are extracted. A feature selection mechanism with minimum redundancy is constructed to screen the optimal sensitive feature set. Secondly, based on adaptive feature fusion, the optimal sensitive feature set is dynamically fused, and the spurious fluctuations of the health index are corrected using linear regression and the 3σ principle. Next, a bottom-up time series segmentation method is employed to divide the health status of the Improved Health Indicators. Finally, a remaining useful life prediction model based on the autoregressive integrated moving average model is established. This study demonstrates that the proposed method effectively identifies features that are most sensitive to degradation trends, accurately determines the initial fault moment of bearings, and achieves effective prediction of the remaining useful life of bearings.

Details DOI

IROS Conference 2023 Conference Paper

Design and Development of a Rapidly Deployable Low-Cost Tensegrity In-Pipe Robot

Yixiang Liu
Xiaolin Dai
Kai Guo
Jiang Wu 0018
Rui Song 0002
Jie Zhao 0003
Yibin Li 0001

Existing in-pipe robots have insufficient adaptability when dealing with accidents in unfamiliar pipe environments. Developing a pipe robot that can be designed and manufactured quickly is one solution. The tensegrity structure is a self-stressing spatial structure formed by the interaction of rigid members and flexible cables, which has the advantages of simple structure, good flexibility, deformability, and impact resistance. Inspired by this structure, we design a novel worm-like tensegrity robot for different pipe environments, which can be manufactured rapidly at low cost. Firstly, a robotic module based on the tensegrity structure is designed inspired by the motion patterns of worm-like organisms. Then, the design process of the module is presented based on the mathematical analysis of the deformation. Finally, a prototype of the tensegrity robot is developed using simple and low-cost parts in less than an hour. To test the motion performance, load performance, and inspection capability of the tensegrity robot, we designed a series of experiments on horizontal pipes, vertical pipes, elbows, and steel pipes. Experimental results show that the worm-like tensegrity robot is simple in structure, easy to manufacture, low in cost, and good in performance.

Details

EAAI Journal 2023 Journal Article

Simulation-based multi-objective optimization towards proactive evacuation planning at metro stations

Kai Guo
Limao Zhang
Maozhi Wu

Effective evacuation management is crucial in response to an emergency at metro stations. Due to the unpredictability and high complexity at metro stations, great challenges exist for evacuation management. A hybrid approach with the integration of building information modeling (BIM), simulation tool (Anylogic), and machine learning algorithms is proposed in this research to realize the evacuation event simulation and proactive evacuation management. A case study is performed to test the applicability and effectiveness of the proposed approach. It is found in the case study that: (1) The constructed simulation model could successfully perform the prediction of the evacuation process for the target metro station, and numbers of congestion areas can be identified (i. e. , 7, 7, 9, 11 congestion areas for the four typical scenarios, respectively); (2) A proactive evacuation guiding strategy is proposed from the hybrid approach, which could realize a much better improvement for the evacuation events (at least 15. 3% and 39. 3% could be achieved for objectives of the evacuation time and the evacuation over-density rate, respectively), compared to the conventional guiding strategies; (3) The proposed proactive guiding strategy is the only one, in all three guiding strategies, that could shorten the evacuation time to the maximum extent and remove the congestion areas entirely. The novelty of the proposed approach lies in that: (i) The proposed hybrid approach could be able to accurately predict the evacuation conditions under different scenarios by incorporating the LightGBM algorithm; (ii) A proactive guiding strategy, along with the proposal of the innovative over-density rate rule, is provided with the ability of significantly improving the evacuation efficiency. This proposed approach not only presents an efficient tool for the evaluation of evacuations, but also greatly enriches the field of proactive evacuation management at metro stations.

Details DOI

AAAI Conference 2022 Conference Paper

Orthogonal Graph Neural Networks

Kai Guo
Kaixiong Zhou
Xia Hu
Yu Li
Yi Chang
Xin Wang

Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations. These models rely on message passing and feature transformation functions to encode the structural and feature information from neighbors. However, stacking more convolutional layers significantly decreases the performance of GNNs. Most recent studies attribute this limitation to the over-smoothing issue, where node embeddings converge to indistinguishable vectors. Through a number of experimental observations, we argue that the main factor degrading the performance is the unstable forward normalization and backward gradient resulted from the improper design of the feature transformation, especially for shallow GNNs where the over-smoothing has not happened. Therefore, we propose a novel orthogonal feature transformation, named Ortho- GConv, which could generally augment the existing GNN backbones to stabilize the model training and improve the model’s generalization performance. Specifically, we maintain the orthogonality of the feature transformation comprehensively from three perspectives, namely hybrid weight initialization, orthogonal transformation, and orthogonal regularization. By equipping the existing GNNs (e. g. GCN, JKNet, GCNII) with Ortho-GConv, we demonstrate the generality of the orthogonal feature transformation to enable stable training, and show its effectiveness for node and graph classification tasks.

PDF Details