Search Results for author:
Found 25 papers, 14 papers with code
Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
The token influence can be measured in a single pass with a fixed reference model or iteratively with self-evolving reference models.
Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels
Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards.
Reassessing Layer Pruning in LLMs: New Insights and Methods
Layer pruning, as a simple yet effective compression method, removes layers of a model directly, reducing computational overhead.
Improving Data Efficiency via Curating LLM-Driven Rating Systems
Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws.
Label Smoothing Improves Machine Unlearning
Taking inspiration from the influence of label smoothing on model confidence and differential privacy, we propose a simple gradient-based MU approach that uses an inverse process of label smoothing.
FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning
The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches.
Fairness Without Harm: An Influence-Guided Active Sampling Approach
In this work, we aim to train models that mitigate group fairness disparity without causing harm to model accuracy.
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
Given the cost and difficulty of cleaning these datasets by humans, we introduce a systematic framework for evaluating the credibility of datasets, identifying label errors, and evaluating the influence of noisy labels in the curated language data, specifically focusing on unsafe comments and conversation classification.
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.
Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes
Our theoretical analyses show that directly using proxy models can give a false sense of (un)fairness.
To Aggregate or Not? Learning with Separate Noisy Labels
The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e. g., via crowdsourcing).
Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features
We observe that tasks with lower-quality features fail to meet the anchor-point or clusterability condition, due to the coexistence of both uninformative and informative representations.
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions.
Mitigating Memorization of Noisy Labels via Regularization between Representations
Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs).
The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
Semi-supervised learning (SSL) has demonstrated its potential to improve the model accuracy for a variety of learning tasks when the high-quality supervised data is severely limited.
Detecting Corrupted Labels Without Training a Model to Predict
In this paper, from a more data-centric perspective, we propose a training-free solution to detect corrupted labels.
A Good Representation Detects Noisy Labels
In this paper, given good representations, we propose a universally applicable and training-free solution to detect noisy labels.
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points.
Image Classification with Human Noise
Image Classification with Label Noise
+1
A Second-Order Approach to Learning with Instance-Dependent Label Noise
We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable.
Identification of 27 abnormalities from multi-lead ECG signals: An ensembled Se-ResNet framework with Sign Loss function
Cardiovascular disease is a major threat to health and one of the primary causes of death globally.
Federated Bandit: A Gossiping Approach
Motivated by the proposal of federated learning, we aim for a solution with which agents will never share their local observations with a central entity, and will be allowed to only share a private copy of his/her own information with their neighbors.
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting.
Image Classification with Label Noise
Learning with noisy labels
Policy Learning Using Weak Supervision
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).
Online optimal task offloading with one-bit feedback
In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model.
Learn and Pick Right Nodes to Offload
An effective task offloading strategy is needed to utilize the computational resources efficiently.
