Search Results for author:
Found 42 papers, 25 papers with code
UniBrain: Universal Brain MRI Diagnosis with Hierarchical Knowledge-enhanced Pre-training
Magnetic resonance imaging~(MRI) have played a crucial role in brain disease diagnosis, with which a range of computer-aided artificial intelligence methods have been proposed.
Bag of Tricks for Long-Tailed Multi-Label Classification on Chest X-Rays
Clinical classification of chest radiography is particularly challenging for standard machine learning algorithms due to its inherent long-tailed and multi-label nature.
Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning
By dynamically manipulating the gradient during training based on these factors, BDR can effectively alleviate knowledge destruction and improve knowledge reconstruction.
On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored.
Zero-shot Composed Text-Image Retrieval
In this paper, we consider the problem of composed image retrieval (CIR), it aims to train a model that can fuse multi-modal information, e. g., text and images, to accurately retrieve images that match the query, extending the user's expression ability.
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
Based on such insights, we propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Exploring Model Dynamics for Accumulative Poisoning Discovery
In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information.
Class-Balancing Diffusion Models
To tackle this problem, we set from the hypothesis that the data distribution is not class-balanced, and propose Class-Balancing Diffusion Models (CBDM) that are trained with a distribution adjustment regularizer as a solution.
Towards Efficient Task-Driven Model Reprogramming with Foundation Models
Moreover, the data used for pretraining foundation models are usually invisible and very different from the target data of downstream tasks.
Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
Privacy and security concerns in real-world applications have led to the development of adversarially robust federated models.
Latent Class-Conditional Noise Model
We solve this problem by introducing a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework.
Long-Tailed Partial Label Learning via Dynamic Rebalancing
The straightforward combination of LT and PLL, i. e., LT-PLL, suffers from a fundamental dilemma: LT methods build upon a given class distribution that is unavailable in PLL, and the performance of PLL is severely influenced in long-tailed context.
Federated Domain Generalization With Generalization Adjustment
Federated Domain Generalization (FedDG) attempts to learn a global model in a privacy-preserving manner that generalizes well to new clients possibly with domain shift.
FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous conditions.
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension
One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i. e., subnet).
Device-Cloud Collaborative Recommendation via Meta Controller
To overcome this issue, we propose a meta controller to dynamically manage the collaboration between the on-device recommender and the cloud-based recommender, and introduce a novel efficient sample construction from the causal perspective to solve the dataset absence issue of meta controller.
Contrastive Learning with Boosted Memorization
Different from previous works, we explore this direction from an alternative perspective, i. e., the data perspective, and propose a novel Boosted Contrastive Learning (BCL) method.
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.
$\alpha$-Weighted Federated Adversarial Training
Federated Adversarial Training (FAT) helps us address the data privacy and governance issues, meanwhile maintains the model robustness to the adversarial attack.
Click-through Rate Prediction with Auto-Quantized Contrastive Learning
Click-through rate (CTR) prediction becomes indispensable in ubiquitous web recommendation applications.
MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation
With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks.
Cooperative Learning for Noisy Supervision
Learning with noisy labels has gained the enormous interest in the robust deep learning area.
Reliable Adversarial Distillation with Unreliable Teachers
However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students.
Contrastive Attraction and Contrastive Repulsion for Representation Learning
We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.
Device-Cloud Collaborative Learning for Recommendation
With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features.
Collaborative Label Correction via Entropy Thresholding
Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels.
Learning with Group Noise
Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels.
Sparse-Interest Network for Sequential Recommendation
Our sparse-interest module can adaptively infer a sparse set of concepts for each user from the large concept pool and output multiple embeddings accordingly.
Learning on Attribute-Missing Graphs
Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.
Decoupled Variational Embedding for Signed Directed Networks
Comprehensive results on both link sign prediction and node recommendation task demonstrate the effectiveness of DVE.
Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Low-dimensional embeddings of knowledge graphs and behavior graphs have proved remarkably powerful in varieties of tasks, from predicting unobserved edges between entities to content recommendation.
Node Attribute Generation on Graphs
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
We further generalize LCCN for open-set noisy labels and the semi-supervised setting.
Ranked #33 on
Image Classification
on Clothing1M
(using extra training data)
How does Disagreement Help Generalization against Label Corruption?
Learning with noisy labels is one of the hottest problems in weakly-supervised learning.
Ranked #13 on
Learning with noisy labels
on CIFAR-10N-Worst
Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels
To handle these issues, by using the memorization effects of deep neural networks, we may train deep neural networks on the whole dataset only the first few iterations.
Variational Collaborative Learning for User Probabilistic Representation
Conventional CF-based methods use the user-item interaction data as the sole information source to recommend items to users.
Understanding VAEs in Fisher-Shannon Plane
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables.
Masking: A New Perspective of Noisy Supervision
It is important to learn various types of classifiers given training data with noisy labels.
Ranked #39 on
Image Classification
on Clothing1M
(using extra training data)
Variational Composite Autoencoders
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable.
Degeneration in VAE: in the Light of Fisher Information Loss
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representation learning.
Collaborative Learning for Weakly Supervised Object Detection
For object detection, taking WSDDN-like architecture as weakly supervised detector sub-network and Faster-RCNN-like architecture as strongly supervised detector sub-network, we propose an end-to-end Weakly Supervised Collaborative Detection Network.
Deep Learning from Noisy Image Labels with Quality Embedding
However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches.
