Search Results for author:
Found 9 papers, 5 papers with code
Spectral Co-Distillation for Personalized Federated Learning
Personalized federated learning (PFL) has been widely investigated to address the challenge of data heterogeneity, especially when a single generic model is inadequate in satisfying the diverse performance requirements of local clients simultaneously.
The Role of Federated Learning in a Wireless World with Foundation Models
Foundation models (FMs) are general-purpose artificial intelligence (AI) models that have recently enabled multiple brand-new generative AI applications.
GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence
To tackle the limitation of entropy maximization, we propose $(\alpha, \beta)$-generalized KL divergence, $\mathcal{D}_{\text{KL}}^{\alpha, \beta}(p\|q)$, which can be used to identify significantly more NC instances.
Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
We introduce algebraic machine reasoning, a new reasoning framework that is well-suited for abstract reasoning.
FedCorr: Multi-Stage Federated Learning for Label Noise Correction
Although there exist methods in centralized learning for tackling label noise, such methods do not perform well on heterogeneous label noise in FL settings, due to the typically smaller sizes of client datasets and data privacy requirements in FL.
Dynamic Attention-based Communication-Efficient Federated Learning
Federated learning (FL) offers a solution to train a global machine learning model while still maintaining data privacy, without needing access to data stored locally at the clients.
Training Classifiers that are Universally Robust to All Label Noise Levels
In particular, we shall assume that a small subset of any given noisy dataset is known to have correct labels, which we treat as "positive", while the remaining noisy subset is treated as "unlabeled".
Ranked #7 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
An information-theoretic framework for learning models of instance-independent label noise
At the heart of our framework is a discriminator that predicts whether an input dataset has maximum Shannon entropy, which shall be used on multiple new datasets $\hat{\mathcal{D}}$ synthesized from $\mathcal{D}$ via the insertion of additional label noise.
A closer look at the approximation capabilities of neural networks
(ii) There exists some $\lambda>0$ (depending only on $f$ and $\sigma$), such that the UAP still holds if we restrict all non-bias weights $w$ in the first layer to satisfy $|w|>\lambda$.
