1 code implementation • 26 May 2025 • Yige Yuan, Teng Xiao, Shuchang Tao, Xue Wang, Jinyang Gao, Bolin Ding, Bingbing Xu
Our findings show that supervision from significantly weaker reasoners can substantially improve student reasoning performance, recovering close to 94% of the gains of expensive RL at a fraction of the cost.
1 code implementation • 26 May 2025 • Yige Yuan, Teng Xiao, Li Yunfan, Bingbing Xu, Shuchang Tao, Yunqi Qiu, HuaWei Shen, Xueqi Cheng
In contrast to expensive search over the discrete space, SEA directly adapts original responses from the base policy toward the optimal one via gradient-based sampling in continuous latent space.
1 code implementation • 28 Feb 2025 • Xueyun Tian, Wei Li, Bingbing Xu, Yige Yuan, Yuanzhuo Wang, HuaWei Shen
Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a state-of-the-art in the new task of instruction-based subject-driven editing.
1 code implementation • 20 Nov 2024 • Yige Yuan, Bingbing Xu, Hexiang Tan, Fei Sun, Teng Xiao, Wei Li, HuaWei Shen, Xueqi Cheng
Confidence calibration in LLMs, i. e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs.
no code implementations • 12 Oct 2024 • Yige Yuan, Bingbing Xu, Teng Xiao, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models.
no code implementations • 25 May 2024 • Zixu Wang, Bingbing Xu, Yige Yuan, HuaWei Shen, Xueqi Cheng
Graph contrastive learning (GCL), standing as the dominant paradigm in the realm of graph pre-training, has yielded considerable progress.
1 code implementation • 1 Feb 2024 • Boshen Shi, Yongqing Wang, Fangda Guo, Bingbing Xu, HuaWei Shen, Xueqi Cheng
To the best of our knowledge, this paper is the first survey for graph domain adaptation.
1 code implementation • CVPR 2024 • Yige Yuan, Bingbing Xu, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng
To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.
no code implementations • 18 Aug 2023 • Wendong Bi, Xueqi Cheng, Bingbing Xu, Xiaoqian Sun, Li Xu, HuaWei Shen
Transfer learning has been a feasible way to transfer knowledge from high-quality external data of source domains to limited data of target domains, which follows a domain-level knowledge transfer to learn a shared posterior distribution.
1 code implementation • IEEE 39th International Conference on Data Engineering (ICDE) 2023 • Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Bingbing Xu, Liang Zeng, Chenxing Wang
To capture these intricate dependencies, spatio-temporal networks, such as recurrent neural networks with graph convolution networks, graph convolution networks with temporal convolution networks, and temporal attention networks with full graph attention networks, are applied.
Ranked #4 on
Traffic Prediction
on PeMSD8
1 code implementation • 25 May 2023 • Yige Yuan, Bingbing Xu, Bo Lin, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.
no code implementations • 25 May 2023 • Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu, Bingbing Xu, Xueqi Cheng
To address these limitations, we analyze the causalities in graph adversarial attacks and conclude that causal features are key to achieve graph adversarial robustness, owing to their determinedness for labels and invariance across attacks.
1 code implementation • 2 Feb 2023 • Wendong Bi, Bingbing Xu, Xiaoqian Sun, Li Xu, HuaWei Shen, Xueqi Cheng
To combat the above challenges, we propose Knowledge Transferable Graph Neural Network (KT-GNN), which models distribution shifts during message passing and representation learning by transferring knowledge from vocal nodes to silent nodes.
1 code implementation • 31 Jan 2023 • Wendong Bi, Bingbing Xu, Xiaoqian Sun, Zidong Wang, HuaWei Shen, Xueqi Cheng
However, most nodes in the tribe-style graph lack attributes, making it difficult to directly adopt existing graph learning methods (e. g., Graph Neural Networks(GNNs)).
no code implementations • 20 Nov 2022 • Yige Yuan, Bingbing Xu, HuaWei Shen, Qi Cao, Keting Cen, Wen Zheng, Xueqi Cheng
Guided by the bound, we design a GCL framework named InfoAdv with enhanced generalization ability, which jointly optimizes the generalization metric and InfoMax to strike the right balance between pretext task fitting and the generalization ability on downstream tasks.
no code implementations • 16 Nov 2022 • Yang Li, Bingbing Xu, Qi Cao, Yige Yuan, HuaWei Shen
On account that previous studies either lacks variance analysis or only focus on a particular sampling paradigm, we firstly propose an unified node sampling variance analysis framework and analyze the core challenge "circular dependency" for deriving the minimum variance sampler, i. e., sampling probability depends on node embeddings while node embeddings can not be calculated until sampling is finished.
1 code implementation • 19 Oct 2022 • Kaike Zhang, Qi Cao, Gaolin Fang, Bingbing Xu, Hongjian Zou, HuaWei Shen, Xueqi Cheng
Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years.
no code implementations • 22 Mar 2022 • Zhaohui Wang, Qi Cao, HuaWei Shen, Bingbing Xu, Xueqi Cheng
The expressive power of message passing GNNs is upper-bounded by Weisfeiler-Lehman (WL) test.
no code implementations • 6 Dec 2021 • Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Bingbing Xu, Chenxing Wang, Liang Zeng
Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to three aspects: i) current existing works mostly exploit intricate temporal patterns (e. g., the short-term thunderstorm and long-term daily trends) within a single method, which fail to accurately capture spatio-temporal dependencies under different schemas; ii) the under-exploration of the graph positional encoding limit the extraction of spatial information in the commonly used full graph attention network; iii) the quadratic complexity of the full graph attention introduces heavy computational needs.
1 code implementation • 27 Jul 2020 • Bingbing Xu, Hua-Wei Shen, Qi Cao, Keting Cen, Xue-Qi Cheng
Graph convolutional networks gain remarkable success in semi-supervised learning on graph structured data.
no code implementations • 27 Jul 2020 • Bingbing Xu, Jun-Jie Huang, Liang Hou, Hua-Wei Shen, Jinhua Gao, Xue-Qi Cheng
Graph neural networks (GNNs) achieve remarkable success in graph-based semi-supervised node classification, leveraging the information from neighboring nodes to improve the representation learning of target node.
no code implementations • 20 Jun 2019 • Keting Cen, Hua-Wei Shen, Jinhua Gao, Qi Cao, Bingbing Xu, Xue-Qi Cheng
In this paper, we address attributed network embedding from a novel perspective, i. e., learning node context representation for each node via modeling its attributed local subgraph.
1 code implementation • ICLR 2019 • Bingbing Xu, Hua-Wei Shen, Qi Cao, Yunqi Qiu, Xue-Qi Cheng
We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform.
Ranked #51 on
Node Classification
on Pubmed