Search Results for author:
Found 23 papers, 17 papers with code
RECOST: External Knowledge Guided Data-efficient Instruction Tuning
When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected with a higher probability than other samples.
Debiased Sample Selection for Combating Noisy Labels
To address this limitation, we propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection.
Energy-based Automated Model Evaluation
The core of the MDE is to establish a meta-distribution statistic, on the information (energy) associated with individual samples, then offer a smoother representation enabled by energy-based learning.
FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models
While copious solutions, such as active learning for small language models (SLMs) and prevalent in-context learning in the era of large language models (LLMs), have been proposed and alleviate the labeling burden to some extent, their performances are still subject to human intervention.
Revisiting the Knowledge Injection Frameworks
Briefly, the core of this technique is rooted in an ideological emphasis on the pruning and purification of the external knowledge base to be injected into LLMs.
Towards Domain-Specific Features Disentanglement for Domain Generalization
Distributional shift between domains poses great challenges to modern machine learning algorithms.
CAME: Contrastive Automated Model Evaluation
In this work, we propose Contrastive Automatic Model Evaluation (CAME), a novel AutoEval framework that is rid of involving training set in the loop.
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise.
TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate.
Towards Cross-Table Masked Pretraining for Web Data Mining
Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information.
A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
In this paper, we propose a generalized URE that can be equipped with arbitrary loss functions while maintaining the theoretical guarantees, given unlabeled data for LAC.
Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility
With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses.
Latent Processes Identification From Multi-View Time Series
Understanding the dynamics of time series data typically requires identifying the unique latent factors for data generation, \textit{a. k. a.
Deep Partial Multi-Label Learning with Graph Disambiguation
In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels.
Controllable Textual Inversion for Personalized Text-to-Image Generation
The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts.
iDAG: Invariant DAG Searching for Domain Generalization
In this work, we first characterize that this failure of conventional ML models in DG is attributed to an inadequate identification of causal structures.
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.
ProMix: Combating Label Noise via Maximizing Clean Sample Utility
To overcome the potential side effect of excessive clean set selection procedure, we further devise a novel SSL framework that is able to train balanced and unbiased classifiers on the separated clean and noisy samples.
Ranked #1 on
Learning with noisy labels
on CIFAR-10N-Worst
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
Contrastive Label Disambiguation for Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
At each node in the hierarchy, a small DNN identifies a different attribute of the query image.
The Emerging Trends of Multi-Label Learning
Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data.
Unified framework for modeling multivariate distributions in biological sequences
Revealing the functional sites of biological sequences, such as evolutionary conserved, structurally interacting or co-evolving protein sites, is a fundamental, and yet challenging task.
Quantitative Methods
