Search Results for author:
Found 201 papers, 97 papers with code
Searching to Exploit Memorization Effect in Learning with Noisy Labels
Sample selection approaches are popular in robust learning from noisy labels.
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.
Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation
Then, we transform the facial expression representation to a neutral representation by simulating the difference in text embeddings from textual facial expression to textual neutral.
Facial Expression Recognition
Facial Expression Recognition (FER)
Text-based Talking Video Editing with Cascaded Conditional Diffusion
The cascaded conditional diffusion model decomposes the complex talking editing task into two flexible generation tasks, which provides a generalizable talking-face representation, seamless audio-visual transitions, and identity-preserved faces on a small dataset.
Robust Learning under Hybrid Noise
To address the challenge, we propose a novel unified learning framework called "Feature and Label Recovery" (FLR) to combat the hybrid noise from the perspective of data recovery, where we concurrently reconstruct both the feature matrix and the label matrix of input data.
Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning
The compelling goal of eradicating undesirable data behaviors, while preserving usual model functioning, underscores the significance of machine unlearning within the domain of large language models (LLMs).
Decoupling the Class Label and the Target Concept in Machine Unlearning
Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class, through gradient ascent on the forgetting data or fine-tuning with the remaining data.
How Interpretable Are Interpretable Graph Neural Networks?
Extracting the desired interpretable subgraph requires an accurate approximation of SubMT, yet we find that the existing XGNNs can have a huge gap in fitting SubMT.
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
In this paper, we propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to Envision potential Outlier Exposure, termed EOE, without access to any actual OOD data.
Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
While Positive-Unlabeled (PU) learning is vital in many real-world scenarios, its application to graph data still remains under-explored.
MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
In cross-domain few-shot classification, \emph{nearest centroid classifier} (NCC) aims to learn representations to construct a metric space where few-shot classification can be performed by measuring the similarities between samples and the prototype of each class.
Federated Learning with Bilateral Curation for Partially Class-Disjoint Data
Partially class-disjoint data (PCDD), a common yet under-explored data formation where each client contributes a part of classes (instead of all classes) of samples, severely challenges the performance of federated algorithms.
Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning without amending the impact on both cross-modal and intra-modal geometrical structures in multimodal learning.
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulnerable to multi-step adversarial attacks.
Balancing Similarity and Complementarity for Federated Learning
Our framework aims to approximate an optimal cooperation network for each client by optimizing a weighted sum of model similarity and feature complementarity.
Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generation
We design a Hierarchical Adaptive Alignment model to concurrently learn the fine-grained fragment correspondence between two modalities and align these representations of fragments in three levels.
MCM: Multi-condition Motion Synthesis Framework
Conditional human motion synthesis (HMS) aims to generate human motion sequences that conform to specific conditions.
Ranked #3 on
Motion Synthesis
on HumanML3D
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.
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.
Few-Shot Adversarial Prompt Learning on Vision-Language Models
The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs.
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.
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.
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.
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.
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.
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.
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.
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.
Understanding Robust Overfitting from the Feature Generalization Perspective
Given that the only difference between adversarial and natural training lies in the inclusion of adversarial perturbations, we further hypothesize that adversarial perturbations degrade the generalization of features in natural data and verify this hypothesis through extensive experiments.
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.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
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.
Moderately Distributional Exploration for Domain Generalization
We show that MODE can endow models with provable generalization performance on unknown target domains.
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
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Robust Generalization against Corruptions via Worst-Case Sharp ness Minimization
Robust generalization aims to deal with the most challenging data distributions which are rarely presented in training set and contain severe noise corruptions.
Zero3D: Semantic-Driven Multi-Category 3D Shape Generation
Semantic-driven 3D shape generation aims to generate 3D objects conditioned on text.
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.
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.
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.
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).
Ranked #26 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
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.
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Adversarial training (AT) with imperfect supervision is significant but receives limited attention.
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
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.
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.
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.
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.
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.
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.
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.
Efficient Private SCO for Heavy-Tailed Data via Averaged Clipping
We consider stochastic convex optimization for heavy-tailed data with the guarantee of being differentially private (DP).
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.
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.
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.
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.
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.
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.
MSR: Making Self-supervised learning Robust to Aggressive Augmentations
With the training going on, the model begins to overfit noisy pairs.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
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.
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.
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.
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.
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.
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.
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).
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.
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.
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.
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.
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 #14 on
Image Generation
on STL-10
$\alpha$-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.
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.
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.
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.
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.
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.
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.
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.
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.
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
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).
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.
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.
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.
CausalAdv: Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
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.
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
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).
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).
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)
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.
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.
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.
Confusable Learning for Large-class Few-Shot Classification
Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.
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.
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.
Geometry-aware Instance-reweighted Adversarial Training
The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy.
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.
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.