Search Results for author:
Found 27 papers, 10 papers with code
Normalize Then Propagate: Efficient Homophilous Regularization for Few-shot Semi-Supervised Node Classification
In this paper, we first analyze the restrictions of GNNs generalization from the perspective of supervision signals in the context of few-shot semi-supervised node classification.
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
However, recent research shows that the visual modality in VLMs is highly vulnerable, allowing attackers to bypass safety alignment in LLMs through visually transmitted content, launching harmful attacks.
GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck
The key idea behind GaGSL is to learn a compact and informative graph structure for node classification tasks.
Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise
Next, we propose a clean labels oriented link that connects unlabeled nodes to cleanly labeled nodes, aimed at mitigating label sparsity and promoting supervision propagation.
Parameterize Structure with Differentiable Template for 3D Shape Generation
Extensive evaluations demonstrate the superiority of our method on reconstruction from point cloud, generation, and interpolation.
Similarity-Navigated Conformal Prediction for Graph Neural Networks
In this paper, we empirically show that for each node, aggregating the non-conformity scores of nodes with the same label can improve the efficiency of conformal prediction sets while maintaining valid marginal coverage.
Safety Alignment for Vision Language Models
To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images.
FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants
Federated learning (FL) provides a privacy-preserving approach for collaborative training of machine learning models.
Understanding Data Augmentation from a Robustness Perspective
In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness.
LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels
We introduce LaplaceConfidence, a method that to obtain label confidence (i. e., clean probabilities) utilizing the Laplacian energy.
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world.
Symmetric Shape-Preserving Autoencoder for Unsupervised Real Scene Point Cloud Completion
Extensive experiments and comparisons demonstrate our superiority and generalization and show that our method achieves state-of-the-art performance on unsupervised completion of real scene objects.
MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentation
Based on the analysis of the internal mechanisms, we develop a mask-based boosting method for data augmentation that comprehensively improves several robustness measures of AI models and beats state-of-the-art data augmentation approaches.
Spatial-Temporal Graph Convolutional Gated Recurrent Network for Traffic Forecasting
We design an attention module to capture long-term dependency by mining periodic information in traffic data.
Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models
With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned.
READ: Aggregating Reconstruction Error into Out-of-distribution Detection
We propose a novel method, READ (Reconstruction Error Aggregated Detector), to unify inconsistencies from classifier and autoencoder.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation
We propose in this paper an end-to-end network, named CS-Net, to complete the point clouds contaminated by noises or containing outliers.
Tailor Versatile Multi-modal Learning for Multi-label Emotion Recognition
Previous methods mainly focus on projecting multiple modalities into a common latent space and learning an identical representation for all labels, which neglects the diversity of each modality and fails to capture richer semantic information for each label from different perspectives.
Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise
We show that our method successfully alleviates the damage of both label noise and confirmation bias.
Ranked #2 on
Image Classification
on mini WebVision 1.0
Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
The proposed method firstly generates and augments the pseudo-source domain, and then employs distribution alignment with four novel losses based on pseudo-label based strategy.
AdaRNN: Adaptive Learning and Forecasting of Time Series
This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data.
Semi-Supervised Learning with Multi-Head Co-Training
Co-training, extended from self-training, is one of the frameworks for semi-supervised learning.
Cross-domain error minimization for unsupervised domain adaptation
Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
Learning transferable and discriminative features for unsupervised domain adaptation
In this paper, a novel method called \textit{learning TransFerable and Discriminative Features for unsupervised domain adaptation} (TFDF) is proposed to optimize these two objectives simultaneously.
Dual Adversarial Domain Adaptation
Recent experiments have shown that when the discriminator is provided with domain information in both domains and label information in the source domain, it is able to preserve the complex multimodal information and high semantic information in both domains.
Ranked #6 on
Domain Adaptation
on ImageCLEF-DA
Homogeneous Online Transfer Learning with Online Distribution Discrepancy Minimization
In this paper, we propose a novel online transfer learning method which seeks to find a new feature representation, so that the marginal distribution and conditional distribution discrepancy can be online reduced simultaneously.
Many could be better than all: A novel instance-oriented algorithm for Multi-modal Multi-label problem
The quality of data collected from different channels are inconsistent and some of them may not benefit for prediction.
