Search Results for author:
Found 185 papers, 86 papers with code
Masking: A New Perspective of Noisy Supervision
It is important to learn various types of classifiers given training data with noisy labels.
Ranked #42 on
Image Classification
on Clothing1M
(using extra training data)
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training.
Ranked #8 on
Learning with noisy labels
on CIFAR-10N-Random3
Searching to Exploit Memorization Effect in Learning from Corrupted Labels
Sample selection approaches are popular in robust learning from noisy labels.
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e. g., images), studies on graph data are still limited.
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models.
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.
Are Anchor Points Really Indispensable in Label-Noise Learning?
Existing theories have shown that the transition matrix can be learned by exploiting \textit{anchor points} (i. e., data points that belong to a specific class almost surely).
Ranked #18 on
Learning with noisy labels
on CIFAR-10N-Random3
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data.
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Despite remarkable success in various applications, large language models (LLMs) are vulnerable to adversarial jailbreaks that make the safety guardrails void.
A Survey of Label-noise Representation Learning: Past, Present and Future
Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios.
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-100N
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.
Part-dependent Label Noise: Towards Instance-dependent Label Noise
Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise.
Geometry-aware Instance-reweighted Adversarial Training
The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy.
CausalAdv: Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning.
Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning
In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift.
Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
Unfortunately, it is challenging to distinguish MGTs and human-written texts because the distributional discrepancy between them is often very subtle due to the remarkable performance of LLMs.
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability
Recently Graph Injection Attack (GIA) emerges as a practical attack scenario on Graph Neural Networks (GNNs), where the adversary can merely inject few malicious nodes instead of modifying existing nodes or edges, i. e., Graph Modification Attack (GMA).
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples.
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.
Understanding and Improving Early Stopping for Learning with Noisy Labels
Instead of the early stopping, which trains a whole DNN all at once, we initially train former DNN layers by optimizing the DNN with a relatively large number of epochs.
Ranked #8 on
Learning with noisy labels
on CIFAR-10N-Aggregate
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.
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.
Out-of-distribution Detection with Implicit Outlier Transformation
It leads to a min-max learning scheme -- searching to synthesize OOD data that leads to worst judgments and learning from such OOD data for uniform performance in OOD detection.
Ranked #12 on
Out-of-Distribution Detection
on ImageNet-1k vs Textures
Combating Representation Learning Disparity with Geometric Harmonization
Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios.
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
However, it has been shown that the MMD test is unaware of adversarial attacks -- the MMD test failed to detect the discrepancy between natural and adversarial data.
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
To defend against MI attacks, previous work utilizes a unilateral dependency optimization strategy, i. e., minimizing the dependency between inputs (i. e., features) and outputs (i. e., labels) during training the classifier.
Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features.
FasTer: Fast Tensor Completion with Nonconvex Regularization
Due to the easy optimization, the convex overlapping nuclear norm has been popularly used for tensor completion.
Variational Imitation Learning with Diverse-quality Demonstrations
Learning from demonstrations can be challenging when the quality of demonstrations is diverse, and even more so when the quality is unknown and there is no additional information to estimate the quality.
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes.
AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning
An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step.
Watermarking for Out-of-distribution Detection
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models.
Ranked #20 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
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).
Instance-dependent Label-noise Learning under a Structural Causal Model
In particular, we show that properly modeling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
Moderately Distributional Exploration for Domain Generalization
We show that MODE can endow models with provable generalization performance on unknown target domains.
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Adversarial training (AT) with imperfect supervision is significant but receives limited attention.
Exploiting Class Activation Value for Partial-Label Learning
As the first contribution, we empirically show that the class activation map (CAM), a simple technique for discriminating the learning patterns of each class in images, is surprisingly better at making accurate predictions than the model itself on selecting the true label from candidate labels.
Understanding Robust Overfitting of Adversarial Training and Beyond
Here, we explore the causes of robust overfitting by comparing the data distribution of \emph{non-overfit} (weak adversary) and \emph{overfitted} (strong adversary) adversarial training, and observe that the distribution of the adversarial data generated by weak adversary mainly contain small-loss data.
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices.
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs).
Provably End-to-end Label-Noise Learning without Anchor Points
In label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers.
Ranked #14 on
Learning with noisy labels
on CIFAR-100N
Probabilistic Margins for Instance Reweighting in Adversarial Training
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights.
Robust Training of Federated Models with Extremely Label Deficiency
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency.
NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels
First, we thoroughly investigate noisy labels (NLs) injection into AT's inner maximization and outer minimization, respectively and obtain the observations on when NL injection benefits AT.
Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.
Hard Sample Matters a Lot in Zero-Shot Quantization
Nonetheless, we find that the synthetic samples constructed in existing ZSQ methods can be easily fitted by models.
Adjustment and Alignment for Unbiased Open Set Domain Adaptation
In a nutshell, ANNA consists of Front-Door Adjustment (FDA) to correct the biased learning in the source domain and Decoupled Causal Alignment (DCA) to transfer the model unbiasedly.
Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
These hard samples are then employed to promote the quality of the ensemble model by adjusting the ensembling weights for each client model.
TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
To this end, we propose a target orientated hypothesis adaptation network (TOHAN) to solve the FHA problem, where we generate highly-compatible unlabeled data (i. e., an intermediate domain) to help train a target-domain classifier.
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training.
Ranked #10 on
Image Generation
on STL-10
Label-Noise Learning with Intrinsically Long-Tailed Data
In this case, it is hard to distinguish clean samples from noisy samples on the intrinsic tail classes with the unknown intrinsic class distribution.
REMAST: Real-time Emotion-based Music Arrangement with Soft Transition
Music as an emotional intervention medium has important applications in scenarios such as music therapy, games, and movies.
Regularly Truncated M-estimators for Learning with Noisy Labels
However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples; (b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization.
Combating Bilateral Edge Noise for Robust Link Prediction
To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse.
Modeling Adversarial Noise for Adversarial Training
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
Improving Adversarial Robustness via Mutual Information Estimation
To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method.
Towards Lightweight Black-Box Attacks against Deep Neural Networks
As it is hard to mitigate the approximation error with few available samples, we propose Error TransFormer (ETF) for lightweight attacks.
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.
Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis
Based on this fact, we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction: one for learning INRs, and the other for learning-to-learn INRs.
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end.
Learning Diverse-Structured Networks for Adversarial Robustness
In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST).
FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
Therefore, the label guidance on labeled data is hard to be propagated to unlabeled data.
Learning to Augment Distributions for Out-of-Distribution Detection
Accordingly, we propose Distributional-Augmented OOD Learning (DAL), alleviating the OOD distribution discrepancy by crafting an OOD distribution set that contains all distributions in a Wasserstein ball centered on the auxiliary OOD distribution.
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available.
MCM: Multi-condition Motion Synthesis Framework for Multi-scenario
We also introduce a Transformer-based diffusion model MWNet (DDPM-like) as our main branch that can capture the spatial complexity and inter-joint correlations in motion sequences through a channel-dimension self-attention module.
Detecting Out-of-distribution Data through In-distribution Class Prior
In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data. Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
To this end, we suggest that generated data (with mistaken OOD generation) can be used to devise an auxiliary OOD detection task to facilitate real OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
Federated Learning with Extremely Noisy Clients via Negative Distillation
The model trained on noisy labels serves as a `bad teacher' in knowledge distillation, aiming to decrease the risk of providing incorrect information.
MCM: Multi-condition Motion Synthesis Framework
Conditional human motion synthesis (HMS) aims to generate human motion sequences that conform to specific conditions.
Ranked #2 on
Motion Synthesis
on HumanML3D
Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation
Wildly Unsupervised Domain Adaptation
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.
Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
To deduce new facts on a knowledge graph (KG), a link predictor learns from the graph structure and collects local evidence to find the answer to a given query.
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable.
Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions
This paper bridges the gap by proposing a pairwise framework for noisy node classification on graphs, which relies on the PI as a primary learning proxy in addition to the pointwise learning from the noisy node class labels.
Federated Noisy Client Learning
Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy.
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a problem has drawn much attention.
Towards out-of-distribution generalizable predictions of chemical kinetics properties
Under this framework, we create comprehensive datasets to benchmark (1) the state-of-the-art ML approaches for reaction prediction in the OOD setting and (2) the state-of-the-art graph OOD methods in kinetics property prediction problems.
Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization Feature Space
We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution.
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.
Understanding Fairness Surrogate Functions in Algorithmic Fairness
To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem.
Matrix Co-completion for Multi-label Classification with Missing Features and Labels
We consider a challenging multi-label classification problem where both feature matrix $\X$ and label matrix $\Y$ have missing entries.
Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling
Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis.
Post-edit Analysis of Collective Biography Generation
Text generation is increasingly common but often requires manual post-editing where high precision is critical to end users.
:telephone::person::sailboat::whale::okhand:; or "Call me Ishmael" - How do you translate emoji?
We report on an exploratory analysis of Emoji Dick, a project that leverages crowdsourcing to translate Melville's Moby Dick into emoji.
On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent
The convergence of Stochastic Gradient Descent (SGD) using convex loss functions has been widely studied.
HSR: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection
By employing hierarchical feature selection, we can compress the scale and dimension of global dictionary, which directly contributes to the decrease of computational cost in sparse representation that our approach is strongly rooted in.
RMSE-ELM: Recursive Model based Selective Ensemble of Extreme Learning Machines for Robustness Improvement
It becomes a potential framework to solve robustness issue of ELM for high-dimensional blended data in the future.
LARSEN-ELM: Selective Ensemble of Extreme Learning Machines using LARS for Blended Data
Extreme learning machine (ELM) as a neural network algorithm has shown its good performance, such as fast speed, simple structure etc, but also, weak robustness is an unavoidable defect in original ELM for blended data.
Privacy-preserving Stochastic Gradual Learning
PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL).
Photometric Redshift Estimation for Quasars by Integration of KNN and SVM
The massive photometric data collected from multiple large-scale sky surveys offer significant opportunities for measuring distances of celestial objects by photometric redshifts.
Instrumentation and Methods for Astrophysics
DATELINE: Deep Plackett-Luce Model with Uncertainty Measurements
Then, we present a weighted Plackett-Luce model to solve the second issue, where the weight is a dynamic uncertainty vector measuring the worker quality.
Twitter Geolocation Prediction Shared Task of the 2016 Workshop on Noisy User-generated Text
This paper presents the shared task for English Twitter geolocation prediction in WNUT 2016.
Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative
May there be a new sample selection method that can outperform the latest importance reweighting method in the deep learning age?
Towards Robust ResNet: A Small Step but A Giant Leap
Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization.
VILD: Variational Imitation Learning with Diverse-quality Demonstrations
However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts and amateurs.
SUM: Suboptimal Unitary Multi-task Learning Framework for Spatiotemporal Data Prediction
However, such a method have relatively weak performance when the task number is small, and we cannot integrate it into non-linear models.
Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples.
Learning with Multiple Complementary Labels
In this paper, we propose a novel problem setting to allow MCLs for each example and two ways for learning with MCLs.
Confidence Scores Make Instance-dependent Label-noise Learning Possible
We find with the help of confidence scores, the transition distribution of each instance can be approximately estimated.
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
Hitherto, the distributional-assumption-free CPE methods rely on a critical assumption that the support of the positive data distribution cannot be contained in the support of the negative data distribution.
Multi-Class Classification from Noisy-Similarity-Labeled Data
We further estimate the transition matrix from only noisy data and build a novel learning system to learn a classifier which can assign noise-free class labels for instances.
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not.
Provably Consistent Partial-Label Learning
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels.
Searching to Exploit Memorization Effect in Learning with Noisy Labels
Sample selection approaches are popular in robust learning from noisy labels.
ADD-Defense: Towards Defending Widespread Adversarial Examples via Perturbation-Invariant Representation
Motivated by this observation, we propose a defense framework ADD-Defense, which extracts the invariant information called \textit{perturbation-invariant representation} (PIR) to defend against widespread adversarial examples.
Robust early-learning: Hindering the memorization of noisy labels
The \textit{early stopping} method therefore can be exploited for learning with noisy labels.
Ranked #32 on
Image Classification
on mini WebVision 1.0
(ImageNet Top-1 Accuracy metric)
Pointwise Binary Classification with Pairwise Confidence Comparisons
To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed.
Confusable Learning for Large-class Few-Shot Classification
Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
We also instantiate our framework with different combinations, which set the new state of the art on benchmark-simulated and real-world datasets with noisy labels.
Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels
The traditional transition matrix is limited to model closed-set label noise, where noisy training data has true class labels within the noisy label set.
Understanding the Interaction of Adversarial Training with Noisy Labels
A recent adversarial training (AT) study showed that the number of projected gradient descent (PGD) steps to successfully attack a point (i. e., find an adversarial example in its proximity) is an effective measure of the robustness of this point.
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.
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.
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Motivated by that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i. e., Bayes-label transition matrix (BLTM)) and learn a classifier to predict Bayes optimal labels.
Instance Correction for Learning with Open-set Noisy Labels
Lots of approaches, e. g., loss correction and label correction, cannot handle such open-set noisy labels well, since they need training data and test data to share the same label space, which does not hold for learning with open-set noisy labels.
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
In this way, we also give large-loss but less selected data a try; then, we can better distinguish between the cases (a) and (b) by seeing if the losses effectively decrease with the uncertainty after the try.
Ranked #26 on
Image Classification
on mini WebVision 1.0
Towards Defending against Adversarial Examples via Attack-Invariant Features
However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.
KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation
However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images.
Local Reweighting for Adversarial Training
However, when tested on attacks different from the given attack simulated in training, the robustness may drop significantly (e. g., even worse than no reweighting).
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.
Click-through Rate Prediction with Auto-Quantized Contrastive Learning
Click-through rate (CTR) prediction becomes indispensable in ubiquitous web recommendation applications.
Can Label-Noise Transition Matrix Help to Improve Sample Selection and Label Correction?
Existing methods for learning with noisy labels can be generally divided into two categories: (1) sample selection and label correction based on the memorization effect of neural networks; (2) loss correction with the transition matrix.
Modeling Adversarial Noise for Adversarial Defense
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
$\alpha$-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.
PI-GNN: Towards Robust Semi-Supervised Node Classification against Noisy Labels
Semi-supervised node classification on graphs is a fundamental problem in graph mining that uses a small set of labeled nodes and many unlabeled nodes for training, so that its performance is quite sensitive to the quality of the node labels.
Co-variance: Tackling Noisy Labels with Sample Selection by Emphasizing High-variance Examples
The sample selection approach is popular in learning with noisy labels, which tends to select potentially clean data out of noisy data for robust training.
Universal Semi-Supervised Learning
Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i. e., class set) and feature distribution (i. e., feature domain) are different between labeled dataset and unlabeled dataset.
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.
Wildly Unsupervised Domain Adaptation and Its Powerful and Efficient Solution
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD---we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation
Wildly Unsupervised Domain Adaptation
Class2Simi: A New Perspective on Learning with Label Noise
It is worthwhile to perform the transformation: We prove that the noise rate for the noisy similarity labels is lower than that of the noisy class labels, because similarity labels themselves are robust to noise.
DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets
In this paper, we propose DeepMix, a mobility-aware, lightweight, and hybrid 3D object detection framework for improving the user experience of AR/MR on mobile headsets.
Do We Need to Penalize Variance of Losses for Learning with Label Noise?
Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels.
Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization
While the optimization problem is nonconvex and nonsmooth, we show that its critical points still have good statistical performance on the tensor completion problem.
Pluralistic Image Completion with Probabilistic Mixture-of-Experts
Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well.
FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels
Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices.
Counterfactual Fairness with Partially Known Causal Graph
Interestingly, we find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided: the sensitive attributes do not have ancestors in the causal graph.
MSR: Making Self-supervised learning Robust to Aggressive Augmentations
With the training going on, the model begins to overfit noisy pairs.
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers.
Efficient Private SCO for Heavy-Tailed Data via Clipping
In this paper, we resolve this issue and derive the first high-probability bounds for the private stochastic method with clipping.
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.
Strength-Adaptive Adversarial Training
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
Is Out-of-Distribution Detection Learnable?
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
Zero3D: Semantic-Driven Multi-Category 3D Shape Generation
Semantic-driven 3D shape generation aims to generate 3D objects conditioned on text.
Towards Zero-trust Security for the Metaverse
By focusing on immersive interaction among users, the burgeoning Metaverse can be viewed as a natural extension of existing social media.
Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation
Motivated by this simple but effective learning pattern, we propose a General-Specific Learning Mechanism (GSLM) to explicitly drive a coarse-grained CAM to a fine-grained pseudo mask.
Federated Semi-Supervised Learning with Annotation Heterogeneity
Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data.
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.
SketchFFusion: Sketch-guided image editing with diffusion model
Sketch-guided image editing aims to achieve local fine-tuning of the image based on the sketch information provided by the user, while maintaining the original status of the unedited areas.
Making Binary Classification from Multiple Unlabeled Datasets Almost Free of Supervision
Training a classifier exploiting a huge amount of supervised data is expensive or even prohibited in a situation, where the labeling cost is high.
A Universal Unbiased Method for Classification from Aggregate Observations
This motivates the study on classification from aggregate observations (CFAO), where the supervision is provided to groups of instances, instead of individual instances.
Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels
In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data.
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC).
Exploiting Counter-Examples for Active Learning with Partial labels
In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process.
Holistic Label Correction for Noisy Multi-Label Classification
The issues are, that we do not understand why label dependence is helpful in the problem, and how to learn and utilize label dependence only using training data with noisy multiple labels.
Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples
As selected data have high discrepancies in probabilities, the divergence of two networks can be maintained by training on such data.
On the Onset of Robust Overfitting in Adversarial Training
Adversarial Training (AT) is a widely-used algorithm for building robust neural networks, but it suffers from the issue of robust overfitting, the fundamental mechanism of which remains unclear.
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting.
Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization
By fully exploring both variant and invariant parameters, our EVIL can effectively identify a robust subnetwork to improve OOD generalization.
Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
To tackle this issue, we propose a method to abstract the collective information of atomic groups into a few $\textit{Neural Atoms}$ by implicitly projecting the atoms of a molecular.
Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes
Surprisingly, DeepSet outperforms transformers across a variety of distribution shifts, implying that preserving permutation invariance symmetry to input demonstrations is crucial for OOD ICL.
Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and their respective impacts.
Enhancing Evolving Domain Generalization through Dynamic Latent Representations
However, in non-stationary tasks where new domains evolve in an underlying continuous structure, such as time, merely extracting the invariant features is insufficient for generalization to the evolving new domains.
Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications.
Discovery of the Hidden World with Large Language Models
The rise of large language models (LLMs) that are trained to learn rich knowledge from the massive observations of the world, provides a new opportunity to assist with discovering high-level hidden variables from the raw observational data.
FedImpro: Measuring and Improving Client Update in Federated Learning
First, we analyze the generalization contribution of local training and conclude that this generalization contribution is bounded by the conditional Wasserstein distance between the data distribution of different clients.
Mitigating Label Noise on Graph via Topological Sample Selection
Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world graph data is noisily labeled.
NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
Hence, NoiseDiffusion performs interpolation within the noisy image space and injects raw images into these noisy counterparts to address the challenge of information loss.
Do CLIPs Always Generalize Better than ImageNet Models?
The performance drops from the common to counter groups quantify the reliance of models on spurious features (i. e., backgrounds) to predict the animals.
Tackling Noisy Labels with Network Parameter Additive Decomposition
Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization.
Few-Shot Adversarial Prompt Learning on Vision-Language Models
The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention.
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases.
On the Learnability of Out-of-distribution Detection
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
