Unsupervised pre-training improves model generalization, but lacks theoretical understanding.
problem Lack of theoretical understanding of unsupervised pre-training's impact on model generalization.
method Introduces a novel theoretical framework to analyze and enhance generalization.
result Enhances understanding of unsupervised pre-training and fine-tuning, proposing a new regularization method.
Paper shows pre-training and transfer learning reduce sample complexity for neural networks.
problem Training high-dimensional supervised learning with limited labeled data.
method Study of single-layer neural networks via online stochastic gradient descent, considering concept shift.
result Pre-training and transfer learning reduce sample complexity by polynomial factors under general assumptions.
Unsupervised pre-training preserves multiple views from input distribution.
problem Learning from multiple views of supervision in unsupervised settings.
method Investigates unsupervised pre-training under information theory, focusing on disentanglement and multiple views.
result Unsupervised pre-training helps conserve multiple views from input distribution, improving model performance.
Paper explores unsupervised transfer learning for SLU, improving model performance with unlabeled data.
problem Improving SLU model performance with limited labeled data.
method Uses ELMo embeddings for unsupervised pre-training and ELMo-Light for faster pre-training. Combines unsupervised and supervised transfer techniques.
result Unsupervised pre-training on unlabeled data significantly improves SLU performance, even outperforming conventional supervised transfer.
Pre-trains deep networks on random labels for improved supervised learning.
problem Improving supervised learning performance with limited labeled data.
method Randomly labels all samples in an unlabeled dataset and trains a deep neural network to memorize these labels.
result Improves classification accuracy by 1.5% to 5% on various action recognition datasets.
Study compares deep feature methods for anomaly detection in limited data scenarios.
problem Handling limited data in industrial inspection applications.
method Three approaches (KNN, Mahalanobis, PaDiM) using pre-trained deep features with data augmentation.
result Data augmentation significantly improves performance in small data regimes.
Novel unsupervised relation extraction framework using BERT.
problem Relation extraction without supervision.
method Syntactic parsing, pre-trained embeddings, distant supervision, fine-tuning BERT.
result Significantly outperforms baselines and matches state-of-the-art in three out of four data sets.
Transformers can learn spectral methods and perform unsupervised learning.
problem Learning spectral methods using unsupervised learning.
method Using multi-layered Transformers, pre-trained on a large set of instances, to learn and perform statistical estimation tasks.
result Proven that pre-trained Transformers can learn spectral methods and perform tasks like PCA and clustering.
Improved DRL performance with novel pre-training method.
problem Data inefficiency in DRL algorithms.
method Jointly pre-training with supervised, autoencoder, and value losses.
result Significantly improved learning performance in Atari games.
POUF fine-tunes large models without labeled data.
problem Lack of labeled data for fine-tuning large pre-trained models.
method Prompt-oriented unsupervised fine-tuning.
result Consistent improvements across various tasks.
Polish hate speech detection team second in PolEval 2019.
problem Low-resource hate speech detection in Polish.
method Fine-tuning ULMFiT and BERT models, automated feature engineering with TPOT.
result TPOT's shallow model achieved second place in PolEval 2019.
Deep neural network predicts finger counting and numerosity estimation.
problem Developing a model for predicting finger counting and numerosity estimation.
method The model is trained in an unsupervised manner using RBMs or autoencoders, then supervised. Finger counting positions are also generated.
result The model shows similarities to human subitizing behavior and confirms the importance of unsupervised training.
Behavior Transfer improves reinforcement learning by leveraging pre-trained policies.
problem Efficient transfer of knowledge in reinforcement learning.
method Behavior Transfer (BT) that uses pre-trained policies for exploration.
result BT combined with pre-training leads to better solutions than without pre-training.
Unified QuesNet learns comprehensive representations for diverse test questions.
problem Lack of labeled data for test questions in online learning systems.
method Unified framework and two-level hierarchical pre-training algorithm for unsupervised learning of heterogeneous question representations.
result QuesNet effectively learns comprehensive question representations and outperforms existing methods.
SMILES Transformer learns molecular fingerprints for drug discovery.
problem Poor performance of rule-based molecular fingerprints in shallow prediction models or small datasets.
method Unsupervised pre-training of a sequence-to-sequence language model on a corpus of SMILES.
result SMILES Transformer outperformed existing methods in small-data settings.
We solve a key problem in cross-lingual learning using a novel approach.
problem Aligning word embeddings across different languages.
method We devise a direct solution to the Wasserstein-Procrustes problem.
result Our method improves existing UCL approaches significantly.
Wind energy forecasting helps to manage power production, and hence, reduces energy cost. Deep Neural Networks (DNN) mimics hierarchical learning in the human brain and thus possesses hierarchical, distributed, and multi-task learning capabilities. Based on aforementioned characteristics, we report Deep Belief Network …
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
Novel approach trains ASR models with less supervision using bilevel optimization.
problem Training acoustic models for ASR with minimal supervision.
method Bilevel optimization with unsupervised and supervised losses.
result Achieves superior performance compared to existing methods.
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adap…
MARGE learns to reconstruct text by paraphrasing, achieving strong performance across multiple tasks.
problem Training sequence-to-sequence models with limited supervision.
method Unsupervised multi-lingual multi-document paraphrasing objective.
result Strong zero-shot performance on document translation and various tasks in multiple languages.
New unsupervised learning task improves RL performance.
problem Reward-driven feature learning limitations in RL from images.
method Introduce Augmented Temporal Contrast (ATC) for unsupervised learning of image representations.
result Training encoders using ATC matches or outperforms end-to-end RL in most environments.
In this paper, we present a statistical-mechanical analysis of deep learning. We elucidate some of the essential components of deep learning---pre-training by unsupervised learning and fine tuning by supervised learning. We formulate the extraction of features from the training data as a margin criterion in a high-dime…
Generative AI decodes quantum codes without labeled data.
problem Efficient decoding of quantum error-correcting codes.
method Generative Transformers learn logical operators from unsupervised syndromes.
result Significantly better decoding accuracy than traditional methods.
Pre-trained model from healthy ADLs improves gait pattern classification for Parkinson's disease.
problem Limited training data for deep learning models in healthcare applications.
method Used convolutional autoencoder to extract features from healthy ADLs data and trained a multi-layer perceptron model for Parkinson's disease classification.
result Features extracted from healthy ADLs data can be used to train an effective classification model for Parkinson's disease.
Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec, an unsupervised representation learning algorithm that extends the distribution…
ProtoTransfer learns from unlabeled data to classify unseen tasks.
problem Few-shot classification with limited labeled data.
method Self-supervised prototypical transfer learning.
result ProtoTransfer outperforms unsupervised meta-learning methods.
A single pre-trained agent guides feature selection using knockoffs.
problem Feature selection challenges in AI-readiness of data.
method Generates knockoff features and uses reinforcement learning.
result Optimal feature subset identified with reduced dependency on target variable.
New unsupervised neural network for beamforming masks trained on real noisy speech.
problem Training neural beamforming masks without labeled data.
method Unsupervised training using a likelihood criterion from spatial mixture model.
result Performance comparable to supervised and teacher-trained systems.
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic feature…
Transformers solve Gaussian Mixture Models without supervision.
problem Solving Gaussian Mixture Models (GMMs) unsupervised.
method Proposes TGMM, a transformer-based framework for GMM tasks.
result Transformers can effectively solve GMM tasks, improving upon classical methods.
Author2Vec generates user embeddings from social media data.
problem Generating useful user embeddings from noisy social media data.
method End-to-end neural network with BERT sentence representations and unsupervised pre-training.
result Author2Vec outperforms traditional methods in user classification tasks.
A new unsupervised method separates speech sources without requiring labeled data.
problem Lack of supervised data for effective neural source separation.
method Uses a complex Gaussian mixture model (cGMM) for joint training of separation and localization networks.
result The method outperforms conventional initialization methods in monaural and multichannel separation.
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.
The study enhances financial rule matching using NLP without datasets.
problem Performing semantic matching between financial rules and policies.
method Outperforming pre-trained models with NLP techniques using free resources.
result Improved semantic matching between financial rules and policies.
Paper learns an explainer to interpret CNN features without annotations.
problem Interpreting complex features in CNNs without labeled data.
method Unsupervised learning of an explainer to decompose and reconstruct feature maps.
result Explainer learns to reconstruct CNN features without losing information.
Improved robustness of BERT through orthogonal classifier heads.
problem Improving robustness of language models for smaller datasets.
method Enforces orthogonal classifier heads and adaptively eliminates weaker ones.
result Improves accuracy by +9% on average across datasets.
New method improves ABI for sequential data, reducing forgetting and improving accuracy.
problem Performance degradation of ABI under model misspecification and distribution shifts.
method Decouples simulation-based pre-training from unsupervised SC fine-tuning, using memory buffer and elastic weight consolidation.
result Significant mitigation of forgetting and improved posterior estimates compared to standard simulation-based training.
Enhanced word embeddings boost multiclass text classification accuracy.
problem Improving multiclass text classification accuracy using pre-trained embeddings.
method Proposed word-class embeddings (WCEs) to enhance pre-trained word embeddings.
result WCEs significantly improve multiclass text classification accuracy.
The use of unsupervised data in addition to supervised data in training discriminative neural networks has improved the performance of this clas- sification scheme. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializ…
In this paper we present a unified framework for modeling multi-relational representations, scoring, and learning, and conduct an empirical study of several recent multi-relational embedding models under the framework. We investigate the different choices of relation operators based on linear and bilinear transformatio…
lamBERT learns language and actions using multimodal BERT.
problem Learning language and actions in complex environments.
method Extending BERT to multimodal representation and integrating with reinforcement learning.
result lamBERT model achieved higher rewards in multitask and transfer settings.
Clarifies contributions of model architectures and resources in SOTA language models.
problem Difficulty in disentangling contributions of model architectures and resources.
method Overview of large pre-trained language models, focusing on their use of new architectures and resources.
result Identifies potential starting points for benchmark comparisons and areas for improvement.
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this…
WME generates document embeddings from word embeddings, outperforming state-of-the-art techniques.
problem Lack of unsupervised document embeddings from pre-trained word embeddings.
method Word Mover's Embedding (WME) approach.
result WME consistently matches or outperforms state-of-the-art techniques on various text classification and similarity tasks.
A new clustering method using deep neural networks with size constraints.
problem Clustering high-dimensional data like images, especially when similarity is not well captured by Euclidean distance.
method Rewriting k-means as an optimal transport task, adding entropic regularization, and introducing constraints on cluster sizes. result The proposed method outperforms state-of-the-art clustering methods in unsupervised accuracy.
MANO normalizes logits to estimate test accuracy without labels.
problem Estimating test accuracy of OOD samples without labels.
method Applies Lp norm to normalized logits. result Achieves state-of-the-art performance across various architectures.
Self-supervised learning improves few-shot classification and segmentation on point clouds.
problem Efficiently learn from limited labeled data in point cloud applications.
method Hierarchical cover-tree partitioning for self-supervised pre-training; restricted to support set for few-shot learning.
result Self-supervised learning significantly improves downstream classification and segmentation accuracy.