Search Results for author:
Found 260 papers, 86 papers with code
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.
Accelerating the diffusion-based ensemble sampling by non-reversible dynamics
Compared with the naive parallel-chain SGLD that updates multiple particles independently, ensemble methods update particles with their interactions.
Leveraging Domain-Unlabeled Data in Offline Reinforcement Learning across Two Domains
In this paper, we investigate an offline reinforcement learning (RL) problem where datasets are collected from two domains.
Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
In this paper, we provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator, which has both positive and negative impacts on model predictions.
Reinforcement Learning with Options and State Representation
The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments.
Learning with Noisy Foundation Models
Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning.
VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates
Social networks are often associated with rich side information, such as texts and images.
Generating Chain-of-Thoughts with a Direct Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
In this paper, motivated by Vapnik's principle, we propose a novel comparison-based CoT generation algorithm that directly identifies the most promising thoughts with the noisy feedback from the LLM.
Reinforcement Learning from Bagged Reward: A Transformer-based Approach for Instance-Level Reward Redistribution
Instead, the learner only obtains rewards at the ends of bags, where a bag is defined as a partial sequence of a complete trajectory.
A General Framework for Learning from Weak Supervision
Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment.
Direct Distillation between Different Domains
Then, we build a fusion-activation mechanism to transfer the valuable domain-invariant knowledge to the student network, while simultaneously encouraging the adapter within the teacher network to learn the domain-specific knowledge of the target data.
The Selected-completely-at-random Complementary Label is a Practical Weak Supervision for Multi-class Classification
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong.
Fixed-Budget Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
We show that the upper bound of the probability of error of the CSA algorithm matches a lower bound up to a logarithmic factor in the exponent.
Atom-Motif Contrastive Transformer for Molecular Property Prediction
As motifs in a molecule are significant patterns that are of great importance for determining molecular properties (e. g., toxicity and solubility), overlooking motif interactions inevitably hinders the effectiveness of MPP.
Thompson Exploration with Best Challenger Rule in Best Arm Identification
This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit framework in the canonical single-parameter exponential models.
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks.
Unified Risk Analysis for Weakly Supervised Learning
The analysis component of the framework, viewed as a decontamination process, provides a systematic method of conducting risk rewrite.
Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
We introduce an algorithm named the Generalized Thompson Sampling Explore (GenTS-Explore) algorithm, which is the first algorithm that can work even when the size of the action set is exponentially large in $d$.
Multi-Label Knowledge Distillation
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images
Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network.
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).
An Optimal Algorithm for the Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
In such a case, the R-CPE-MAB can be seen as a special case of the so-called transductive linear bandits.
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.
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.
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
In this paper, we introduce imprecise label learning (ILL), a framework for the unification of learning with various imprecise label configurations.
Ranked #1 on
Learning with noisy labels
on mini WebVision 1.0
Enriching Disentanglement: Definitions to Metrics
Disentangled representation learning is a challenging task that involves separating multiple factors of variation in complex data.
Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation
Our analysis reveals that the efficiency of implicit label sharing is closely related to the performance of existing CLL models.
A Category-theoretical Meta-analysis of Definitions of Disentanglement
Disentangling the factors of variation in data is a fundamental concept in machine learning and has been studied in various ways by different researchers, leading to a multitude of definitions.
Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning
Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data.
Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation.
Fairness Improves Learning from Noisily Labeled Long-Tailed Data
Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning.
The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models
Although the uniform prior is shown to be optimal, we highlight the inherent limitation of its optimality, which is limited to specific parameterizations and emphasizes the significance of the invariance property of priors.
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks.
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models.
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
In addition to the empirical performance, TS has been shown to achieve asymptotic problem-dependent lower bounds in several models.
Robust computation of optimal transport by $β$-potential regularization
Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions.
Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning
Meanwhile, we divide the whole learning task into learning with the large-scale representation models in an unsupervised manner and learning with the small-scale policy model in the RL manner. The small policy model facilitates policy learning, while not sacrificing generalization and expressiveness via the large representation model.
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Adversarial training (AT) with imperfect supervision is significant but receives limited attention.
Generalized Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
\emph{Classification with rejection} (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify.
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift
To formally analyze this issue, we provide a unique algebraic formulation of the combination shift problem based on the concepts of homomorphism, equivariance, and a refined definition of disentanglement.
Adapting to Online Label Shift with Provable Guarantees
In this paper, we formulate and investigate the problem of \emph{online label shift} (OLaS): the learner trains an initial model from the labeled offline data and then deploys it to an unlabeled online environment where the underlying label distribution changes over time but the label-conditional density does not.
Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization
Recent years have witnessed a great success of supervised deep learning, where predictive models were trained from a large amount of fully labeled data.
The Survival Bandit Problem
For that purpose, we identify two key components in the survival regret: the regret given no ruin (which corresponds to the regret in the MAB), and the probability that the procedure is interrupted, called the probability of ruin.
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.
Excess risk analysis for epistemic uncertainty with application to variational inference
Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU).
Universal approximation property of invertible neural networks
Invertible neural networks (INNs) are neural network architectures with invertibility by design.
Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the wanted model is recovered from the modified model.
On the Effectiveness of Adversarial Training against Backdoor Attacks
To explore whether adversarial training could defend against backdoor attacks or not, we conduct extensive experiments across different threat models and perturbation budgets, and find the threat model in adversarial training matters.
Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
Furthermore, we theoretically find that the adversary can also degrade the lower bound of a TST's test power, which enables us to iteratively minimize the test criterion in order to search for adversarial pairs.
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
In contrast to others, our method is model-free and even instance-free.
Towards Adversarially Robust Deep Image Denoising
Secondly, to robustify DIDs, we propose an adversarial training strategy, hybrid adversarial training ({\sc HAT}), that jointly trains DIDs with adversarial and non-adversarial noisy data to ensure that the reconstruction quality is high and the denoisers around non-adversarial data are locally smooth.
Learning with Proper Partial Labels
Recently, various approaches on partial-label learning have been proposed under different generation models of candidate label sets.
Rethinking Importance Weighting for Transfer Learning
A key assumption in supervised learning is that training and test data follow the same probability distribution.
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.
Collaborate to Defend Against Adversarial Attacks
However, an ensemble still wastes the limited capacity of multiple models.
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.
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
Specifically, we disentangle the effects of Adaptive Learning Rate and Momentum of the Adam dynamics on saddle-point escaping and flat minima selection.
Unsupervised Federated Learning is Possible
We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the wanted model is recovered from the modified model.
Does Adversarial Robustness Really Imply Backdoor Vulnerability?
Based on thorough experiments, we find that such trade-off ignores the interactions between the perturbation budget of adversarial training and the magnitude of the backdoor trigger.
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts.
Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences
In this paper, we consider the task of predicting $Y$ from $X$ when we have no paired data of them, but we have two separate, independent datasets of $X$ and $Y$ each observed with some mediating variable $U$, that is, we have two datasets $S_X = \{(X_i, U_i)\}$ and $S_Y = \{(U'_j, Y'_j)\}$.
Positive-Unlabeled Classification under Class-Prior Shift: A Prior-invariant Approach Based on Density Ratio Estimation
Learning from positive and unlabeled (PU) data is an important problem in various applications.
Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
In many real-world imitation learning tasks, the demonstrator and the learner have to act under different observation spaces.
Multi-Class Classification from Single-Class Data with Confidences
We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i. e., the class-posterior probabilities for all the classes) are available.
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.
On the Robustness of Average Losses for Partial-Label Learning
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL).
Loss function based second-order Jensen inequality and its application to particle variational inference
First, we provide a new second-order Jensen inequality, which has the repulsion term based on the loss function.
To Smooth or Not? When Label Smoothing Meets Noisy Labels
We provide understandings for the properties of LS and NLS when learning with noisy labels.
Ranked #9 on
Learning with noisy labels
on CIFAR-10N-Random3
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
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.
A unified view of likelihood ratio and reparameterization gradients
Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine learning and reinforcement learning; however, they are usually explained as simple mathematical tricks, with no insight into their nature.
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.
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks.
Approximating Instance-Dependent Noise via Instance-Confidence Embedding
Label noise in multiclass classification is a major obstacle to the deployment of learning systems.
Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information
In our method, a policy conditioned on a continuous or discrete latent variable is trained by directly maximizing the variational lower bound of the mutual information, instead of using the mutual information as unsupervised rewards as in previous studies.
Lower-Bounded Proper Losses for Weakly Supervised Classification
To this end, we derive a representation theorem for proper losses in supervised learning, which dualizes the Savage representation.
LocalDrop: A Hybrid Regularization for Deep Neural Networks
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas.
Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation
Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions.
Guided Interpolation for Adversarial Training
To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data.
Learning from Similarity-Confidence Data
Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data.
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise activations of adversarial data with those of their natural counterparts.
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 Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks.
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).
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
SSC can be solved by a standard (multi-class) classification method, and we use the SSC solution to obtain the final binary classifier through a certain linear-fractional transformation.
Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics
In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given.
A Symmetric Loss Perspective of Reliable Machine Learning
When minimizing the empirical risk in binary classification, it is a common practice to replace the zero-one loss with a surrogate loss to make the learning objective feasible to optimize.
On the Role of Pre-training for Meta Few-Shot Learning
One is to (pre-)train a classifier with examples from known classes, and then transfer the pre-trained classifier to unknown classes using the new examples.
Combinatorial Pure Exploration with Full-bandit Feedback and Beyond: Solving Combinatorial Optimization under Uncertainty with Limited Observation
Combinatorial optimization is one of the fundamental research fields that has been extensively studied in theoretical computer science and operations research.
On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs).
On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective
In this paper, we first prove that the focal loss is classification-calibrated, i. e., its minimizer surely yields the Bayes-optimal classifier and thus the use of the focal loss in classification can be theoretically justified.
Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
Thus it motivates us to design a similar mechanism named {\it artificial neural variability} (ANV), which helps artificial neural networks learn some advantages from ``natural'' neural networks.
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.
Binary classification with ambiguous training data
This problem is substantially different from semi-supervised learning since unlabeled samples are not necessarily difficult samples.
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.
Classification with Rejection Based on Cost-sensitive Classification
The goal of classification with rejection is to avoid risky misclassification in error-critical applications such as medical diagnosis and product inspection.
Robust Imitation Learning from Noisy Demonstrations
Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning.
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.
Stable Weight Decay Regularization
\citet{loshchilov2018decoupled} demonstrated that $L_{2}$ regularization is not identical to weight decay for adaptive gradient methods, such as Adaptive Momentum Estimation (Adam), and proposed Adam with Decoupled Weight Decay (AdamW).
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.
A One-step Approach to Covariate Shift Adaptation
A default assumption in many machine learning scenarios is that the training and test samples are drawn from the same probability distribution.
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions.
Adai: Separating the Effects of Adaptive Learning Rate and Momentum Inertia
Specifically, we disentangle the effects of Adaptive Learning Rate and Momentum of the Adam dynamics on saddle-point escaping and minima selection.
Online Dense Subgraph Discovery via Blurred-Graph Feedback
Dense subgraph discovery aims to find a dense component in edge-weighted graphs.
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
In this framework, we prove that OGD is robust to Catastrophic Forgetting then derive the first generalisation bound for SGD and OGD for Continual Learning.
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
We answer this question by showing a convenient criterion: a CF-INN is universal if its layers contain affine coupling and invertible linear functions as special cases.
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback.
LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning
The prototypical network (ProtoNet) is a few-shot learning framework that performs metric learning and classification using the distance to prototype representations of each class.
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.
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.
$γ$-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator
Approximate Bayesian computation (ABC) is a likelihood-free inference method that has been employed in various applications.
Pairwise Supervision Can Provably Elicit a Decision Boundary
A classifier built upon the representations is expected to perform well in downstream classification; however, little theory has been given in literature so far and thereby the relationship between similarity and classification has remained elusive.
Rethinking Importance Weighting for Deep Learning under Distribution Shift
Under distribution shift (DS) where the training data distribution differs from the test one, a powerful technique is importance weighting (IW) which handles DS in two separate steps: weight estimation (WE) estimates the test-over-training density ratio and weighted classification (WC) trains the classifier from weighted training data.
Calibrated Surrogate Losses for Adversarially Robust Classification
Adversarially robust classification seeks a classifier that is insensitive to adversarial perturbations of test patterns.
Learning from Aggregate Observations
We study the problem of learning from aggregate observations where supervision signals are given to sets of instances instead of individual instances, while the goal is still to predict labels of unseen individuals.
Do Public Datasets Assure Unbiased Comparisons for Registration Evaluation?
In this study, we use the variogram to screen the manually annotated landmarks in two datasets used to benchmark registration in image-guided neurosurgeries.
Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time
If the black-box function varies with time, then time-varying Bayesian optimization is a promising framework.
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.
Do We Need Zero Training Loss After Achieving Zero Training Error?
We experimentally show that flooding improves performance and, as a byproduct, induces a double descent curve of the test loss.
Progressive Identification of True Labels for Partial-Label Learning
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label.
A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima
Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training deep networks in practice.
Few-shot Domain Adaptation by Causal Mechanism Transfer
We take the structural equations in causal modeling as an example and propose a novel DA method, which is shown to be useful both theoretically and experimentally.
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.
Learning from Noisy Similar and Dissimilar Data
We perform a detailed investigation of this problem under two realistic noise models and propose two algorithms to learn from noisy S-D data.
Binary Classification from Positive Data with Skewed Confidence
Positive-confidence (Pconf) classification [Ishida et al., 2018] is a promising weakly-supervised learning method which trains a binary classifier only from positive data equipped with confidence.
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.
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.
Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples.
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning
We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection.
Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors.
A unified view of likelihood ratio and reparameterization gradients and an optimal importance sampling scheme
Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature.
Learning Only from Relevant Keywords and Unlabeled Documents
We consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given.
Learning from Indirect Observations
Weakly-supervised learning is a paradigm for alleviating the scarcity of labeled data by leveraging lower-quality but larger-scale supervision signals.
Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics
Finally, we investigate the application of multi-agent methods to high-dimensional robotic tasks and show that our approach can be used to learn decentralized policies in this domain.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
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
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.
Constraint Learning for Control Tasks with Limited Duration Barrier Functions
When deploying autonomous agents in unstructured environments over sustained periods of time, adaptability and robustness oftentimes outweigh optimality as a primary consideration.
Are Registration Uncertainty and Error Monotonically Associated
Probabilistic image registration (PIR) methods provide measures of registration uncertainty, which could be a surrogate for assessing the registration error.
Classification from Triplet Comparison Data
Although learning from triplet comparison data has been considered in many applications, an important fundamental question of whether we can learn a classifier only from triplet comparison data has remained unanswered.
Direction Matters: On Influence-Preserving Graph Summarization and Max-cut Principle for Directed Graphs
On the other hand, compressing the vertices while preserving the directed edge information provides a way to learn the small-scale representation of a directed graph.
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
Uncoupled Regression from Pairwise Comparison Data
We propose two practical methods for uncoupled regression from pairwise comparison data and show that the learned regression model converges to the optimal model with the optimal parametric convergence rate when the target variable distributes uniformly.
Fast and Robust Rank Aggregation against Model Misspecification
Specifically, the properties of our CoarsenRank are summarized as follows: (1) CoarsenRank is designed for mild model misspecification, which assumes there exist the ideal preferences (consistent with model assumption) that locates in a neighborhood of the actual preferences.
Calibrated Surrogate Maximization of Linear-fractional Utility in Binary Classification
A clue to tackle their direct optimization is a calibrated surrogate utility, which is a tractable lower bound of the true utility function representing a given metric.
Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero
There have been increasing challenges to solve combinatorial optimization problems by machine learning.
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
Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization
In this paper, we derive an unbiased risk estimator which can handle all of similarities/dissimilarities and unlabeled data.
A Pseudo-Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision
To address the need, we propose a special weakly supervised MLL problem that not only focuses on the situation of limited fine-grained supervision but also leverages the hierarchical relationship between the coarse concepts and the fine-grained ones.
Zero-shot Domain Adaptation Based on Attribute Information
In this paper, we propose a novel domain adaptation method that can be applied without target data.
Polynomial-time Algorithms for Multiple-arm Identification with Full-bandit Feedback
Based on our approximation algorithm, we propose novel bandit algorithms for the top-k selection problem, and prove that our algorithms run in polynomial time.
Online Multiclass Classification Based on Prediction Margin for Partial Feedback
We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness.
New Tricks for Estimating Gradients of Expectations
We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions between samples.
Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization
We further provide an estimation error bound to show that our risk estimator is consistent.
Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation
Appropriately evaluating the discrepancy between domains is essential for the success of unsupervised domain adaptation.
On the Calibration of Multiclass Classification with Rejection
First, we consider an approach based on simultaneous training of a classifier and a rejector, which achieves the state-of-the-art performance in the binary case.
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?
Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric
We consider the problem of learning a binary classifier from only positive and unlabeled observations (called PU learning).
Imitation Learning from Imperfect Demonstration
Imitation learning (IL) aims to learn an optimal policy from demonstrations.
On Symmetric Losses for Learning from Corrupted Labels
This paper aims to provide a better understanding of a symmetric loss.
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis
However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters.
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
Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
However, identifying the hierarchical policy structure that enhances the performance of RL is not a trivial task.
Active Deep Q-learning with Demonstration
In this work, we propose Active Reinforcement Learning with Demonstration (ARLD), a new framework to streamline RL in terms of demonstration efforts by allowing the RL agent to query for demonstration actively during training.
Complementary-Label Learning for Arbitrary Losses and Models
In contrast to the standard classification paradigm where the true class is given to each training pattern, complementary-label learning only uses training patterns each equipped with a complementary label, which only specifies one of the classes that the pattern does not belong to.
Ranked #22 on
Image Classification
on Kuzushiji-MNIST
Classification from Positive, Unlabeled and Biased Negative Data
In binary classification, there are situations where negative (N) data are too diverse to be fully labeled and we often resort to positive-unlabeled (PU) learning in these scenarios.
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.
Improving Generative Adversarial Imitation Learning with Non-expert Demonstrations
Imitation learning aims to learn an optimal policy from expert demonstrations and its recent combination with deep learning has shown impressive performance.
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.
Positive-Unlabeled Classification under Class Prior Shift and Asymmetric Error
Based on the analysis of the Bayes optimal classifier, we show that given a test class prior, PU classification under class prior shift is equivalent to PU classification with asymmetric error.
Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data
In this paper, we propose a novel unified approach to estimating the class-prior and training a classifier alternately.
Dueling Bandits with Qualitative Feedback
We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm.
Clipped Matrix Completion: A Remedy for Ceiling Effects
On the other hand, matrix completion (MC) methods can recover a low-rank matrix from various information deficits by using the principle of low-rank completion.
Unsupervised Domain Adaptation Based on Source-guided Discrepancy
A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain.
On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
In this paper, we study training arbitrary (from linear to deep) binary classifier from only unlabeled (U) data by ERM.
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces
Motivated by the success of reinforcement learning (RL) for discrete-time tasks such as AlphaGo and Atari games, there has been a recent surge of interest in using RL for continuous-time control of physical systems (cf.
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.
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)
Bayesian posterior approximation via greedy particle optimization
Another example is the Stein points (SP) method, which minimizes kernelized Stein discrepancy directly.
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
A Feature-Driven Active Framework for Ultrasound-Based Brain Shift Compensation
Kernels of the GP are estimated by using variograms and a discrete grid search method.
Uplift Modeling from Separate Labels
Uplift modeling is aimed at estimating the incremental impact of an action on an individual's behavior, which is useful in various application domains such as targeted marketing (advertisement campaigns) and personalized medicine (medical treatments).
On the Applicability of Registration Uncertainty
For probabilistic image registration (PIR), the predominant way to quantify the registration uncertainty is using summary statistics of the distribution of transformation parameters.
Binary Matrix Completion Using Unobserved Entries
In this paper, motivated by a semi-supervised classification method recently proposed by Sakai et al. (2017), we develop a method for the BMC problem which can use all of positive, negative, and unobserved entries, by combining the risks of Davenport et al. (2014) and Hsieh et al. (2015).
Variational Inference for Gaussian Process with Panel Count Data
We present the first framework for Gaussian-process-modulated Poisson processes when the temporal data appear in the form of panel counts.
Active Feature Acquisition with Supervised Matrix Completion
Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance.
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model
In this paper, we derive a minimax error rate under more practical setting for a broader class of crowdsourcing models including the DS model as a special case.
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
High sensitivity of neural networks against malicious perturbations on inputs causes security concerns.
Gaussian Process Classification with Privileged Information by Soft-to-Hard Labeling Transfer
A state-of-the-art method of Gaussian process classification (GPC) with privileged information is GPC+, which incorporates privileged information into a noise term of the likelihood.
Classification from Pairwise Similarity and Unlabeled Data
Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high.
Generative Local Metric Learning for Kernel Regression
This paper shows how metric learning can be used with Nadaraya-Watson (NW) kernel regression.
Hierarchical Policy Search via Return-Weighted Density Estimation
Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL).
Binary Classification from Positive-Confidence Data
Can we learn a binary classifier from only positive data, without any negative data or unlabeled data?
Variational Inference based on Robust Divergences
In this paper, based on Zellner's optimization and variational formulation of Bayesian inference, we propose an outlier-robust pseudo-Bayesian variational method by replacing the Kullback-Leibler divergence used for data fitting to a robust divergence such as the beta- and gamma-divergences.
Good Arm Identification via Bandit Feedback
We consider a novel stochastic multi-armed bandit problem called {\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold.
Fully adaptive algorithm for pure exploration in linear bandits
We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly.
Information-Theoretic Representation Learning for Positive-Unlabeled Classification
Recent advances in weakly supervised classification allow us to train a classifier only from positive and unlabeled (PU) data.
Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios
Based on the proposed estimator, novel methods both for mode-seeking clustering and density ridge estimation are developed, and the respective convergence rates to the mode and ridge of the underlying density are also established.
