[PDF] Discovering Latent Class Labels for Multi-Label Learning | Semantic Scholar (2024)

A multi-label classification model based on deep learning is proposed that can simultaneously predict known and unknown labels for unseen images and an attention mechanism is introduced into the model, where the attention maps of unknown labels can be used to observe the corresponding objects of an image.

This paper first presents a general risk formulation for complementary label learning through an adoption of arbitrary losses designed for ordinary-label learning, and theoretically analyzes that the method is applicable for any loss functions to learn deep neural networks with complementary labels in the framework of risk minimization.

This survey paper attempts to create a self-contained guide that gives an in-depth overview of the field of Differential Privacy ML, and proposes a set of specific best practices for stating guarantees.

This work considers the contextual bandit problem where at each time, the agent only has access to a noisy version of the context and the error variance and proposes the first online algorithm with sublinear regret guarantees under mild conditions.

This work proposes a complete framework that takes advantage of collected sensor accelerometer data to generate a human activity behavioral model that can be supportive in predicting future development of human movement disabilities or even in the individual's rehabilitation after a surgery for Osteoarthritis.

This paper is the first to observe that some of this performance can be recovered when training with a loss tailored to DP-SGD; it challenges cross-entropy as the de facto loss for deep learning with DP.

A reparametrization scheme that perturbs the gradients on gradient-carrier matrices and reconstructs an update for the original weight from the noisy gradients, whose optimality is rigorously justified under linear regression and empirically verified with deep learning tasks.

A new taxonomy for privacy risks and protection methods inAVs is provided, and privacy in AVs is categorize into three levels: individual, population, and proprietary .

With GEP, the algorithm achieves decent accuracy with reasonable computational cost and modest privacy guarantee for deep models, and with privacy bound $\epsilon=8, it achieves significantly improving over existing results.

...

...

This paper proposes the first approach to discover multiple novel labels in MIML problem using an efficient augmented lagrangian optimization, which has a bag-dependent loss term and abag-independent clustering regularization term, enabling the known labels and multiple novels to be modeled simultaneously.

This work proposes a new approach called Multi-label learning with Emerging New Labels (MuENL), which has three functions: classify instances on currently known labels, detect the emergence of a new label, and construct a new classifier for each new label that works collaboratively with the classifier for known labels.

MLCT leverages information concerning the co-occurrence of pairwise labels to address the class-imbalance challenge; it introduces a predictive reliability measure to select samples, and applies label-wise filtering to confidently communicate labels of selected samples among co-training classifiers.

An intuitive yet effective algorithm named LIFT, which firstly constructs features specific to each label by conducting clustering analysis on its positive and negative instances, and then performs training and testing by querying the clustering results.

This paper proposes a novel method to construct effective and rich label-specific features through exploring labeled data distribution and leveraging label correlations and employs clustering analysis to explore discriminative features for each tail label replacing the original high-dimensional and sparse features.

Inspired by the research works on modeling high-order label correlations, LLSF is extended to learn class-Dependent Labels in a sparse stackingway, denoted as L LSF-DL, and incorporates both second-order- and high- order label correlations.

A new partial label learning strategy named PL-LE is proposed to learn from partial label examples via label enhancement by leveraging the topological information of the feature space.

iMVWL simultaneously learns a shared subspace from incomplete views with weak labels, the local label structure and the predictor in this subspace, which can not only capture cross-view relationships but also weak-label information of training samples.

...

...