Author name cluster

Weiye Wang

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.

3 papers

2 author rows

IJCAI Conference 2025 Conference Paper

Relation-Augmented Dueling Bayesian Optimization via Preference Propagation

Xiang Xia
Xiang Shu
Shuo Liu
Yiyi Zhu
Yijie Zhou
Weiye Wang
Bingdong Li
Hong Qian

In black-box optimization, when directly evaluating the function values of solutions is very costly or infeasible, access to the objective function is often limited to comparing pairs of solutions, which yields dueling black-box optimization. Dueling optimization is solely based on pairwise preferences, and thus notably reduces cost compared with function value based methods. However, the optimization performance of dueling optimization is often limited due to that most existing dueling optimization methods do not make full use of the pairwise preferences collected. To better utilize these preferences, this paper proposes relation-augmented dueling Bayesian optimization (RADBO) via preference propagation. By considering solution similarity, RADBO aims to uncover the potential dueling relations between solutions within different preferences through the proposed preference propagation technique. Specifically, RADBO first clusters solutions using a Gaussian mixture model. After obtaining the solution set with the highest intra-cluster similarity, RADBO utilizes a directed hypergraph to model the potential dueling relations between solutions, thereby realizing relation augmentation. Extensive experiments are conducted on both synthetic functions and real-world tasks such as motion control, car cab design and spacecraft trajectory optimization. The experimental results disclose the satisfactory accuracy of augmented preferences in RADBO, and show the superiority of RADBO compared with existing dueling optimization methods. Notably, it is verified that, under the same evaluation cost budget, RADBO can be competitive with or even surpass the function value based Bayesian optimization methods with respect to optimization performance.

PDF Details DOI

EAAI Journal 2025 Journal Article

Towards understanding human actions through long-short-term semantic motion encoding

Chaolong Zhang
Yuanping Xu
Zhijie Xu
Chao Kong
Benjun Guo
Jin Jin
Xiaowei Song
Weiye Wang

Human action recognition has achieved competitive performance since the advancement of deep learning and large-scale training datasets. However, recent approaches tend to leverage contextual features instead of interpreting human actions based on semantic definitions. This study presents a long-short-term semantic motion encoding method (LSME) based on human pose sequences, aiming to understand generically semantic action representation over an entire video. The three-dimensional convolutional neural network is proposed to model short-term motions, followed by a two-dimensional temporal convolution for long-term semantic encoding. Finally, the Euclidean distance and Additive Angular Margin Loss based methods are explored to encode action signatures of unseen actions in the open-set recognition problem. Therefore, LSME can understand actual semantic action definitions and recognise unseen actions with negligible data and computational cost adjunction instead of retraining a new model. By fusing a spatial pathway, the proposed model has achieved state-of-the-art performance on action recognition according to the experiments carried out on NTU (Nanyang Technological University) and Kinetics datasets, with the accuracy of 93. 82 % on NTU 60, 53. 04 % top-1 and 79. 32 % top-5 accuracies on Skeleton-Mimetics. These results show that the proposed model is capable of encoding semantic action features whilst speeding up understanding events for real-world applications. It has also demonstrated promising applicability and extensibility for solving challenging real-world human action understanding problems.

Details DOI

ECAI Conference 2024 Conference Paper

High-Dimensional Causal Bayesian Optimization

Yupeng Wu
Weiye Wang
Yangwenhui Zhang
Mingjia Li 0002
Yuanhao Liu
Hong Qian
Aimin Zhou

Causal global optimization (CGO) aims to complete optimization tasks through causal inference. In the high-dimensional CGO problems, traditional causal Bayesian optimization (CBO) methods struggle with the curse of dimensionality attributed to the number of variables in the causal graph, and scale inconsistency among Gaussian Process (GP) models. These issues limit the application of CBO in domains requiring optimization over large causal graphs. To address these limitations, this paper proposes a high-dimensional causal Bayesian optimization (HCBO) algorithm. To address the curse of dimensionality, HCBO introduces a submodularity indicator for variable subsets through the concept of causal intrinsic dimensionality (CID). It then uses the submodular optimization algorithm to find approximations of CID within polynomial sample complexity. Theoretically, we disclose a sufficient condition for CID’s existence. To address the issue of scale inconsistency among GP models, HCBO introduces a scale-normalized scoring function, ensuring stable identification of the optimal GP model corresponding to CID for intervention. Extensive experiments are conducted on high-dimensional synthetic and real-world tasks, i. e. , coral ecology and health. The existence of CID is verified across the datasets of all tasks. HCBO achieves state-of-the-art performance in CGO problems and can handle causal graphs at a scale 10 times larger than that manageable by previous CBO methods.

Details