We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The features extracted with Prototypical Networks are clustered using -means with …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “few labeled examples”
Few-shot graph classification on graphs with limited labeled examples.
problem Limited labeled data for graph classification.
method Graph spectral measures to cluster graphs into super-classes, then use GNNs.
result Improved classification performance on few-shot graph classification tasks.
A framework for using auxiliary data to improve few-shot learning.
problem Few-shot learning with scarce labeled examples and abundant auxiliary data.
method Automatic pseudo-shot selection and masking module to adjust auxiliary features.
result Masking module improves accuracy by 4.68 and 6.03 percentage points.
New algorithm detects rare categories with few labels.
problem Detecting rare categories with limited labeled data.
method Dimension-driven statistics and kappa-profile.
result Algorithm performs well on separable and non-separable classes.
In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different c…
Less-than-one-shot learning tackles few-shot learning with minimal data.
problem Training models on very small datasets while maintaining accuracy.
method Soft-label k-Nearest Neighbors classifier and theoretical lower bounds analysis.
result Achieving learning of multiple classes with fewer than the required samples.
This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes for w…
SCA learns to learn from target-set examples, improving few-shot learning performance.
problem Limited labelled examples in few-shot learning tasks.
method SCA learns a label-free loss function via self-critique and adapts the base-model for new tasks.
result SCA achieves substantially reduced error-rates and state-of-the-art performance.
Meta metric learning improves few-shot learning for diverse domains.
problem Few-shot learning struggles with diverse domains and varying label numbers.
method Task-specific learners with metric learning and a meta learner to discover task-specific metrics.
result Meta metric learning achieves superior performance in diverse multi-domain tasks and flexible label numbers.
Graph-based framework for generalized few-shot learning.
problem Transferring learned models to novel tasks with few labeled examples.
method Graph-based framework that models relationships between seen and novel classes.
result Demonstrates benefits on benchmark datasets.
Theoretical analysis improves few-shot learning performance.
problem Optimizing the number of labeled examples per category in few-shot learning.
method Theoretical analysis of Prototypical Networks, proposing a robust method to the shot number.
result Model trained for arbitrary meta-training shot number performs well across different meta-testing shot numbers.
Enhances few-shot image classification using unlabelled examples.
problem Few-shot image classification with limited labeled data.
method Transductive meta-learning combining soft k-means clustering and neural feature extractor.
result State-of-the-art performance on Meta-Dataset, mini-ImageNet, and tiered-ImageNet benchmarks.
Improved few-shot learning with lower-level neural network embeddings.
problem Limited data scenarios in few-shot learning.
method Graph-based meta-learning framework using hidden layer feature embeddings.
result Utilization of lower-level neural network embeddings improves classifier accuracy.
Adaptive-Step Graph Meta-Learner tackles few-shot graph classification with limited labeled data.
problem Few labeled graph data in bioinformatics and other applications.
method A novel framework combining a graph meta-learner and a step controller for robust and generalization.
result State-of-the-art results on several few-shot graph classification tasks.
Few-shot brain segmentation from weakly labeled data with deep heteroscedastic multi-task networkscs.LG
Few-shot brain segmentation achieved with weak labels and deep networks.
problem Efficient brain segmentation from limited labeled data.
method Heteroscedastic multi-task networks with Monte-Carlo inference and direct probability learning.
result Significant improvements in segmentation accuracy with minimal labeled data.
LLM embeddings improve adaptation to tabular -shifts with few labeled examples.
problem Improving robustness to -shifts in tabular data.
method Serializing tabular data to LLM embeddings and fine-tuning for adaptation.
result LLM embeddings can be adapted to target domains with minimal labeled data.
New algorithm improves GAN performance with minimal labels.
problem Improving GAN performance with little supervision.
method Intentionally corrupts generated labels to match real data statistics, trains discriminator with corrupted labels.
result Minimizing proposed loss is equivalent to minimizing true divergence between real and generated data.
Limited supervision can enable reliable disentangled representation learning.
problem Learning disentangled representations without inductive biases is theoretically impossible.
method Investigated the impact of limited supervision (0.01--0.5% of data) on disentanglement methods.
result A small number of labeled examples (0.01--0.5\% of the data set) is sufficient for model selection.
Big models pretrain and fine-tune for semi-supervised learning on ImageNet.
problem Learning from few labeled examples with a large amount of unlabeled data.
method Unsupervised pretraining of a big ResNet model followed by supervised fine-tuning and distillation.
result 73.9% ImageNet top-1 accuracy with just 1% of labels (13 labeled images per class).
An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that fits the data well by making as few label queries as possible. This work addresses…
Meta learning improves with contextualizers that adapt to examples.
problem Few shot classification with limited labeled data.
method Implement contextualizers as generalizable prototypes for gradient-based meta learning.
result Contextualizers significantly boost performance on various few shot learning datasets.
AAL method generates few-shot tasks from unlabeled data for unsupervised few-shot learning.
problem Lack of unsupervised few-shot learning methods.
method Randomly label a subset of images, apply data augmentation, and use generated labels for target sets.
result Learned models achieve good generalization on Omniglot and Mini-Imagenet.
MeLa learns task relations by inferring global labels for robust FSL.
problem Few-shot learning with limited global labels.
method Meta Label Learning (MeLa) and augmented pre-training.
result MeLa outperforms existing methods across diverse benchmarks.
New method transfers causal mechanisms for few-shot domain adaptation.
problem Few labeled target domain data for regression problems.
method Mechanism transfer using structural equations in causal modeling.
result Method can adapt from apparently different distributions.
Paper proposes Meta Label Learning to infer global labels for robust few-shot models.
problem Few-shot learning with limited training data.
method Meta Label Learning (MeLa) framework that infers global labels.
result MeLa framework is competitive with existing methods and robust for few-shot learning.
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscs.LG
Paper proposes M3S training for GCNs on graphs with few labels.
problem Learning graph embeddings with few labeled nodes is challenging.
method Multi-Stage Self-Supervised (M3S) Training Algorithm combining self-supervised learning.
result M3S Training Algorithm improves GCNs' generalization on graphs with few labeled nodes.
APL learns from surprising observations to quickly generalize from few examples.
problem Quickly generalize from limited data for intelligent systems.
method Approximates probability distributions by remembering surprising observations in an external memory module.
result APL performs as well as state-of-the-art baselines on few-shot classification benchmarks.
SST framework boosts GNN performance on few-labeled graph data.
problem Performance degradation of GNNs on graphs with few labeled nodes.
method Stabilized Self-Training (SST) framework for GNNs.
result SST methods achieve superior performance, especially on graphs with few labeled nodes.
Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inferencestat.ML
Bayesian framework uses unlabeled data to improve fairness assessment.
problem Reliable fairness assessment with limited labeled data.
method Hierarchical latent variable model with Bayesian inference.
result Significant reduction in estimation error for fairness metrics.
LST improves few-shot classification by leveraging unlabeled data and meta-learning.
problem Challenges of few-shot classification due to limited labeled data.
method Semi-supervised meta-learning method (LST) that uses unlabeled data and a soft weighting network (SWN).
result Significant improvements over state-of-the-art methods on ImageNet benchmarks.
Fair-MAML learns fair models from few examples.
problem Lack of data or bias in fairness-relevant tasks.
method Adapted MAML algorithm with fairness regularization.
result Trains fair models from few examples.
Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embeddingcs.LG
MetaTNE tackles few-shot novel labels in graphs, improving node classification.
problem Node classification on graphs with novel labels and limited training data.
method MetaTNE framework with structural, meta-learning, and optimization modules.
result MetaTNE significantly improves node classification over state-of-the-art methods.
TAMA uses LMMs to detect and interpret anomalies in time series data with few labels.
problem Challenges in manual feature engineering and extensive labeled training data for TSAD.
method Leverages LMMs to convert time series into visual formats for few-shot in-context learning.
result Consistently outperforms state-of-the-art methods in TSAD tasks.
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on …
Meta-learning framework for few-shot one-class classification using order-equivariant networks.
problem Few labeled examples for positive class in one-class classification tasks.
method Order-equivariant networks for meta-learning a binary classifier conditioned on positive examples.
result Meta-learning framework outperforms baselines on unseen synthetic streams.
This study explores how examples influence ICL in LLMs.
problem Understanding how examples impact in-context learning in large language models.
method Theoretical study with a probabilistic model extending from Gaussian mixture model.
result The impact of pre-training knowledge and examples on ICL prediction accuracy.
TransMatch uses transfer learning to improve few-shot learning accuracy.
problem Building robust models with limited labeled data.
method Transfer-learning framework combining feature extraction, initialization, and semi-supervised learning.
result Significant improvement in few-shot learning accuracy.
New method improves few-shot learning with noisy labels.
problem Robustness to label noise in few-shot learning.
method Feature aggregation and Transformer model for noisy samples.
result TraNFS outperforms other methods in noisy conditions.
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Datacs.LG
Deep RL detects anomalies from few labeled examples and large unlabeled data.
problem Anomaly detection with limited labeled data and large unlabeled data.
method Deep reinforcement learning to optimize detection of labeled and unlabeled anomalies.
result Significantly outperforms state-of-the-art methods on 48 real-world datasets.
Improved predictions for rare labels using neural networks and ontologies.
problem Long-tailed frequency distribution in multi-label prediction problems.
method Modified neural network output layer with a Bayesian network of sigmoids leveraging ontology relationships.
result Significant improvements in per-label AUROC and average precision for less common labels.
Dynamic text classification with changing labels using learned metrics.
problem Traditional text classifiers struggle with dynamic label sets.
method Replacing fixed output layer with a learned metric space for nearest-neighbor classification.
result Learning a non-Euclidean metric improves performance in low data regimes.
COMET learns concepts for few-shot learning, improving performance.
problem Few-shot learning challenges in machine learning.
method Meta-learning with human-interpretable concept dimensions.
result Significant improvement in 1-shot learning tasks.
New active learning methods use statistical leverage scores to select examples efficiently.
problem Efficiently selecting labeled examples for high model accuracy with limited labeled data.
method Proposes ALEVS and DBALEVS methods based on statistical leverage scores.
result DBALEVS selects diverse, representative examples efficiently.
A method to improve few-shot learning using continual local replacement and pseudo labeling.
problem Learning novel classes with limited data.
method Sophisticated network architecture for feature representation and continual local replacement strategy.
result Significantly improved generalization and better decision boundary for classification.
Early stopping in meta-learning improved by analyzing neural activation patterns.
problem Early stopping in few-shot learning is challenging due to distributional shifts between meta-validation and meta-test sets.
method Activation-Based Early-stopping (ABE) analyzes hidden layer activations from unlabelled support examples to detect when target generalization diverges from source data.
result Simple activation statistics can effectively estimate target generalization, improving few-shot transfer learning across various algorithms and datasets.
The paper proposes methods to predict classifier generalization with few labeled samples.
problem Measuring classifier generalization with limited labeled data.
method Analysis of generalization variability, transfer-based solutions in supervised, semi-supervised, and unsupervised settings.
result Simple measures correlate with classifier generalization and can predict it with confidence.
Graph-based Bayesian SSL uses graph theory to propagate labels from a few to many unlabeled features.
problem Efficiently propagating labels from a small set of labeled data to a large set of unlabeled data.
method Probabilistic framework using graph theory and Bayesian statistics.
result Mathematical foundations for improving the accuracy and efficiency of label propagation.
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Timecs.LG
Few-shot learning benchmarks can be solved without using support set labels at test-time.
problem Evaluate the adequacy of few-shot learning benchmarks that require task supervision at test-time.
method Introduced Centroid Networks, a modification of Prototypical Networks, which hides support set labels from the method at test-time and uses clustering to recover them.
result Most benchmarks cannot be solved perfectly without LT, indicating the inadequacy of benchmarks requiring task supervision.