Self-supervised pretraining for heterogeneous hypergraphs improves graph-based tasks.
problem Capturing higher-order relations in heterogeneous hypergraphs.
method SPHH framework for self-supervised pretraining of heterogeneous HyperGNNs.
result SPHH consistently outperforms state-of-the-art baselines in various downstream tasks.
The study examines pretrained models for few-shot image classification.
problem Improving few-shot classification performance with pretrained models.
method Systematic investigation of pretrained models on Imagenet for few-shot image classification.
result Supervised pretrained models outperform unsupervised models in few-shot classification.
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
Pretraining models improves text classification accuracy, but diminishing returns are observed with large datasets.
problem Improving text classification accuracy with pretrained models.
method Examined the benefits of pretrained models on text classification tasks with varying amounts of training data.
result As the number of training examples grows into the millions, the accuracy gap between pretrained BERT-based models and vanilla LSTM narrows to within 1%.
Mask-reconstruction pretraining helps in downstream tasks by capturing more semantic features.
problem How mask-reconstruction pretraining helps in downstream tasks and why it surpasses supervised learning.
method Theoretical analysis and experimental validation of mask-reconstruction pretraining (MRP) on auto-encoders.
result MRP provably captures more semantic features than supervised learning, leading to better performance in downstream tasks.
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 ( ≤ \le ≤ 13 labeled images per class). CERT improves language understanding by contrastively learning sentence-level semantics.
problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.
This study compares transfer learning and self-supervised learning for better model performance.
problem Choosing between transfer learning and self-supervised learning for optimal model performance.
method Comprehensive comparative study of transfer learning and self-supervised learning under various data and task properties.
result Self-supervised learning outperforms transfer learning in certain applications, and vice versa.
Deep nearest neighbors outperform self-supervised methods in anomaly detection.
problem Anomaly detection using self-supervised deep methods.
method Simple nearest-neighbor approach on Imagenet pretrained features.
result Nearest-neighbor method outperforms self-supervised methods in accuracy, few shot generalization, training time, and noise robustness.
We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by making use of the Contrastive Predictive Coding loss (Oord et al., 2018). Given masked-o…
Unsupervised algorithm parses CSG images into CFG without pretraining.
problem Sparse reward problem in unsupervised program synthesis for images.
method Grammar-encoded tree LSTM, entropy regularization, sampling without replacement.
result Recover meaningful programs in large search spaces (up to 3.8 i m e s 10 28 3.8 imes 10^{28} 3.8 im es 1 0 28 ). Study reveals attributes help in few-shot classification generalization.
problem Understanding what makes some novel classes easier to learn.
method Defined attributes to quantify concept relatedness, used supervised and self-supervised learning.
result Combining self-supervised pretraining with supervised finetuning improves generalization.
Deep Convolutional features extracted from a comprehensive labeled dataset, contain substantial representations which could be effectively used in a new domain. Despite the fact that generic features achieved good results in many visual tasks, fine-tuning is required for pretrained deep CNN models to be more effective …
PULSE learns representations from physiological time series.
problem Lack of effective pretraining objectives for physiological time series.
method Proposes a pretraining framework exploiting dynamical systems generative model.
result PULSE learns representations that distinguish semantic classes and improve transfer learning.
Proposes a new pretraining strategy for RNNs to improve classification performance.
problem Poor generalization of RNNs due to initial parameter assignment.
method Data-aware layer-wise pretraining strategy to initialize RNN parameters.
result Data-aware strategies positively support the initialization of RNN-based classification models.
Advances few-shot classification by treating it as supervised learning and proposing new training techniques.
problem Formulating the ability of humans to learn from limited data in machine learning.
method Formulated few-shot classification as a supervised learning problem and introduced multi-episode and cross-way training techniques.
result Proposed training strategies accelerate the training process without accuracy loss.
New method uses unlabelled data to improve Bayesian Neural Networks.
problem Lack of ability to use unlabelled data in conventional Bayesian Neural Networks.
method Self-supervised Bayesian Neural Networks using contrastive pretraining and variational lower bound optimization.
result Prior predictive distributions capture problem semantics better and improve predictive performance.
Theoretical analysis of data quality and synergies in LLMs.
problem Understanding why different training methods require different amounts of data.
method Theoretical analysis of transformers trained on a weight prediction task for linear regression.
result SFT excels on smaller datasets challenging for the pretrained model, while RL benefits from large, not overly difficult data.
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
Paper analyzes self-supervised learning using causal methods and proposes a new objective.
problem Lack of theoretical understanding of self-supervised learning success.
method Uses a causal framework to enforce invariance constraints on proxy classifiers.
result ReLIC objective improves generalization guarantees and outperforms existing methods.
Self-supervised method detects replay spoofing using acoustic configurations.
problem Challenges in collecting large-scale datasets for replay spoofing detection.
method Self-supervised pretraining of acoustic configurations using existing datasets.
result The method outperforms baseline by 30% on ASVspoof 2019 physical access dataset.
Unsupervised method discovers interpretable directions in GAN latent space.
problem Discovering interpretable directions in GAN latent space without supervision.
method Model-agnostic procedure to identify directions corresponding to semantic manipulations.
result Findings include directions for background removal and competitive saliency detection performance.
Study shows pretraining and finetuning can effectively tackle covariate shift in linear regression.
problem Linear regression under covariate shift where source and target distributions differ but conditional distribution remains similar.
method Pretraining on source data and finetuning on target data using online SGD.
result Transfer learning with O ( N 2 ) O(N^2) O ( N 2 ) source data is as effective as supervised learning with N N N target data. Researchers propose a new SSL risk decomposition method to evaluate and improve self-supervised learning models.
problem Self-supervised learning evaluation is limited to a single metric, providing little insight into model performance and improvement.
method Proposes an SSL risk decomposition that considers four error components: approximation, representation usability, probe generalization, and encoder generalization.
result Analysis of 169 SSL vision models reveals the main sources of error and provides insights for improving SSL models in specific settings.
Paper analyzes why deeper layers of ViTs perform worse on out-of-distribution tasks.
problem Performance degradation of intermediate layers in ViTs under distribution shift.
method Extensive linear probing experiments across various benchmarks and fine-grained analysis of transformer modules.
result Probing feedforward network activations yields best performance under significant distribution shift.
We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting. The Ladder Network distinguishes itself from other semi-supervised methods by jointly optimizing a supervised and unsupervised cost. In many settings this has proven to be more successful than o…
A method for self-supervised learning of multivariate time series data across varying channels.
problem Labeling multivariate biomedical time series data is laborious and expensive.
method Proposes a multi-view self-supervised learning approach using a message passing neural network to extract a single representation across channels.
result Our method, combined with the TS2Vec loss, outperforms all other methods in most settings.
Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the process of feature learning, others pretrain the policies by imitating expert dem…
Protein modeling is an increasingly popular area of machine learning research. Semi-supervised learning has emerged as an important paradigm in protein modeling due to the high cost of acquiring supervised protein labels, but the current literature is fragmented when it comes to datasets and standardized evaluation tec…
This paper proves the theoretical advantage of unsupervised pretraining for machine learning tasks.
problem Understanding why unsupervised pretraining helps in machine learning tasks.
method A generic framework using Maximum Likelihood Estimation (MLE) for unsupervised pretraining and Empirical Risk Minimization (ERM) for downstream tasks.
result Proves an excess risk of i l d e O ( C Φ / m + C Ψ / n ) ilde{\mathcal{O}}(\sqrt{\mathcal{C}_Φ/m} + \sqrt{\mathcal{C}_Ψ/n}) i l d e O ( C Φ / m + C Ψ / n ) for downstream tasks under mild conditions. Two CSSL-based methods improve graph classification with limited labeled data.
problem Limited labeled data for graph classification leads to overfitting.
method Contrastive self-supervised learning (CSSL) for graph encoders pretraining and regularization.
result CSSL methods reduce overfitting and improve graph classification accuracy.
New framework analyzes LLM personalization trade-offs under congestion.
problem Tension between personalization and resource sharing in LLMs.
method Developed a statistical-economic framework to model user incentives.
result Congestion can flip rankings of SFT and ICL, and offers both methods never hurt profits.
We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298). We compa…
The dissertation establishes a contexture theory to mathematically characterize representation learning.
problem The lack of a scientific understanding of representation learning in foundation models.
method Introduces the contexture theory as a unified framework for analyzing representation learning methods.
result Representation learning is optimal when the association between input and context is neither too strong nor too weak.
Flaky performance found in GNN SSL on RDBs, leading to worse linear evaluation.
problem Downstream task performances of GNN SSL on RDBs are poor.
method Proposed InfoNode to maximize mutual information between initial and final node representations.
result InfoNode improves GNN SSL performance on RDBs, supporting conjecture of conflict between SSL and GNN message passing.
Study semi-supervised learning with noisy proxy covariates, deriving bounds and showing gains.
problem Learning from noisy proxy covariates with scarce labels.
method Two-stage estimator learning kernel eigenfeatures from all proxy covariates and fitting a ridge predictor on labeled data.
result Finite sample bounds show fast labeled sample rates and consistent gains over supervised and semi-supervised baselines.
New research shows deep models learn sparse features, limiting transfer learning; ensembling improves performance.
problem Sparse feature learning in deep models limits transfer learning performance.
method Developed a theoretical framework and proposed an ensembling strategy to aggregate multiple models.
result Ensembling yields a 9% improvement in transfer accuracy without extra pretraining cost.
Pretrained time-series models outperform train-from-scratch baselines in financial return forecasting.
problem Financial return forecasting
method Pretrained time-series foundation models
result Pretrained TSFMs dominate the ranking distribution, accounting for 8 of 10 task-level wins.
Unified framework for transfer learning regression without extra cost.
problem Transfer learning for regression models without additional implementation cost.
method Introduces a density-ratio reweighting function estimated via Bayesian framework.
result Unified integration of three TL methods with no extra cost.
Self-supervised learning improves representation from EEG signals without labels.
problem Limited supervised data for EEG signal analysis.
method Predicting temporal context from unlabeled EEG time series.
result Self-supervised approach outperforms supervised methods in low data regimes.
Develops methods for training models with few annotations in computer vision tasks.
problem Training models with limited labeled data in computer vision.
method Theoretical, algorithmic, and experimental contributions for Meta-Learning and Semi-Supervised Learning.
result Improves Contrastive Learning and proposes a semi-supervised method for transformer-based object detectors.
In-context learning solves PU classification without iterative optimization.
problem Binary classification with only labeled positives and unlabeled samples.
method Pretrained transformer (PUICL) that learns from synthetic PU datasets.
result Outperforms four standard PU learning baselines on 20 benchmarks.
Self-supervision improves GCNs' generalizability and robustness.
problem Improving graph convolutional networks' performance.
method Three mechanisms of self-supervision, multi-task learning, and graph adversarial training.
result Self-supervision enhances GCNs' robustness and generalizability.
Study improves cryptocurrency price prediction using unlabeled text data.
problem Predicting cryptocurrency returns from unlabelled text data.
method Introduced weak learning approach to finetune BERT on unlabeled text data.
result Finetuning pretrained NLP models with weak labels enhances forecast accuracy.
New bounds for contrastive learning handle domain shifts and generalization.
problem Domain shifts and generalization challenges in downstream tasks.
method Novel generalization bounds accounting for both domain shift and generalization.
result Performance of contrastively learned representations depends on statistical discrepancy between pretraining and downstream distributions.
Subset selection improves weak supervision performance.
problem Optimizing the use of weakly-labeled data.
method Combining pretrained data representations with the cut statistic for subset selection.
result Subset selection improves weak supervision performance by up to 19%.
SFAVEL distills features from language models for fact verification without annotations.
problem Fact verification with semantically meaningful and compact features.
method Self-supervised pretraining using contrastive loss with language models.
result Achieved state-of-the-art results on FB15k-237 and FEVER.
SSL theory improves representation learning from raw data.
problem Challenges in SSL, including instability and collapse.
method Precise analysis of generalization performance with a theory-friendly setup.
result Insights for SSL practitioners on data augmentation, network architecture, and training algorithm.