Paper tackles label insufficiency and inaccuracy in semi-supervised learning.
problem Label insufficiency and inaccuracy in semi-supervised learning.
method Graph-based propagation for label insufficiency and label filtering for inaccuracy.
result SIIS improves performance in the presence of label noise and scarcity.
Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insuf…
Chinese word segmentation (CWS) is an important task for Chinese NLP. Recently, many neural network based methods have been proposed for CWS. However, these methods require a large number of labeled sentences for model training, and usually cannot utilize the useful information in Chinese dictionary. In this paper, we …
Paper proposes neural approach for Chinese named entity recognition.
problem Challenges in Chinese named entity recognition due to context-dependency and lack of word delimiters.
method Introduces a CNN-LSTM-CRF neural architecture and a unified framework for joint training with word segmentation.
result Improves Chinese named entity recognition performance, especially with limited training data.
New method tackles unknown unknowns in machine learning.
problem Unknown classes in training data misperceived as other labels.
method Exploratory machine learning with rejection model, feature exploration, and model cascade.
result The method discovers potentially hidden classes and improves model performance.
New approach combines invariance and information bottleneck for OOD generalization.
problem OOD generalization failures in classification tasks.
method Revisit linear regression tasks, prove information bottleneck constraint necessary, propose combined approach.
result Combined invariance and information bottleneck approach improves OOD generalization.
New method improves false-/true-positive-rate estimation in fraud detection with noisy labels.
problem Estimating FPR/TPR in fraud detection with class-conditional label noise.
method Directly cleaning model's validation data to de-correlate cleaning error with model scores.
result Improves accuracy of FPR/TPR estimates, especially in asymmetric label noise scenarios.
Deep models can fit noisy labels, but robustness and reliability are still issues.
problem Training deep models with noisy labels leads to unreliable uncertainty quantification.
method Analysis of conditional distribution over noisy labels and evaluation of robust loss functions.
result Strictly proper and robust loss functions preserve accuracy but do not guarantee reliability.
Active learning (AL) repeatedly trains the classifier with the minimum labeling budget to improve the current classification model. The training process is usually supervised by an uncertainty evaluation strategy. However, the uncertainty evaluation always suffers from performance degeneration when the initial labeled …
WD-DTL uses Wasserstein distance to transfer deep features for fault diagnosis.
problem Transfer learning difficulty in diverse working conditions with insufficient labelled data.
method Adversarial training with Wasserstein distance to align feature distributions.
result WD-DTL improves fault diagnosis accuracy in diverse conditions.
Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship. It is critical in many machine learning, pattern recognition and data mining algorithms, and usually require large amount of label information (such as class labels or pair/triplet constraints) to achieve satisfac…
AdaGCN transfers labels across networks via adversarial domain adaptation and graph convolution.
problem Cross-network node classification with limited labeled data.
method Adversarial domain adaptation and graph convolution.
result AdaGCN successfully transfers labels with low labeled data on source networks and significant domain divergence.
A new SOM method learns from both labeled and unlabeled data.
problem Improving performance in semi-supervised learning.
method Adaptive Local Thresholds Semi-Supervised Self-Organizing Map (ALTSS-SOM).
result ALTSS-SOM outperforms other methods in classification and clustering.
New oracle uses uncertainty for active classification with noisy feedback.
problem Improving query complexity in interactive binary classifier learning.
method Proposes a new pairwise comparison oracle that considers uncertainty and an adaptive labeling algorithm.
result Demonstrates improved performance and efficiency compared to existing methods.
Under covariate shift, training (source) data and testing (target) data differ in input space distribution, but share the same conditional label distribution. This poses a challenging machine learning task. Robust Bias-Aware (RBA) prediction provides the conditional label distribution that is robust to the worstcase lo…
Ask-n-Learn uses gradient embeddings for active learning in image classification.
problem Efficiently labeling large amounts of training data for deep models.
method Gradient embeddings based on pseudo-labels, prediction calibration, and data augmentation.
result Significant improvements over state-of-the-art baselines on image classification tasks.
In the absence of prior knowledge, ordinal embedding methods obtain new representation for items in a low-dimensional Euclidean space via a set of quadruple-wise comparisons. These ordinal comparisons often come from human annotators, and sufficient comparisons induce the success of classical approaches. However, colle…
Transfer learning improves HVAC fault detection with minimal labeled data.
problem Lack of labeled data for HVAC system faults.
method Bayesian classifier trained on large data, then transferred to new buildings with few normal operation samples.
result Few samples are sufficient to maintain classifier precision and recall.
New method tackles dynamic data labeling issues with limited labels.
problem Dynamic data labeling with scarce labeled instances.
method Instance exploitation technique for aggressive model adaptation.
result Aggressive model adaptation leads to better performance than standard methods.
This paper presents a novel approach for detection of liver abnormalities in an automated manner using ultrasound images. For this purpose, we have implemented a machine learning model that can not only generate labels (normal and abnormal) for a given ultrasound image but it can also detect when its prediction is like…
ct-SNE extracts hidden structure from labeled data.
problem Insufficient 2D visualization of high-dimensional data.
method Conditional t-SNE discounts prior information from labels.
result Extracts complementary structure not captured by t-SNE alone.
Bayesian approach improves deep learning efficiency.
problem Efficient training of deep learning models with limited labeled data.
method Combines active learning and data augmentation with Bayesian generative models.
result Improves training efficiency and classification accuracy compared to existing methods.
Improves unsupervised domain adaptation by enforcing feature extractor to focus on task-relevant information.
problem Leveraging label information from source domain for accurate target domain models without labels.
method Variational Information Bottleneck (VBDA) method that explicitly enforces feature extractor to ignore irrelevant task factors.
result Significantly outperforms state-of-the-art methods across three domain adaptation benchmark datasets.
Boosting is a general method of generating many simple classification rules and combining them into a single, highly accurate rule. In this talk, I will review the AdaBoost boosting algorithm and some of its underlying theory, and then look at how this theory has helped us to face some of the challenges of applying Ada…
SAM improves neural network generalization better than SGD, especially in noisy data.
problem Overfitting in large neural networks with label noise.
method Sharpness-Aware Minimization (SAM) compared to Stochastic Gradient Descent (SGD).
result SAM prevents noise learning and facilitates feature learning better than SGD.
Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods based on a single view have been extensively studied for information retrieval. However, the representation capacity of a single view is insufficient and some discrimi…
HighwayGraph models long-distance node relations in GNNs with improved performance.
problem Limited-layer information propagation in GNNs hinders long-distance node relation modeling.
method Proposes two solutions: implicit and explicit modeling of long-distance node relations using shallow GNN architectures and a self-training framework.
result HighwayGraph achieves consistent and significant improvements over four GNNs on three benchmark datasets.
This study generates synthetic data to augment sleep apnea detection datasets.
problem Insufficient and unbalanced training datasets for health applications.
method Designing a recurrent Generative Adversarial Network to generate synthetic data and balance the dataset.
result All classifiers exhibit improved performance in sensitivity and kappa statistic.
GCNs favor high-degree nodes, leading to biased performance; a new method mitigates this.
problem Degree-related biases in GCNs, especially for low-degree nodes.
method Developed a novel SL-DSGC that reduces model and data biases.
result SL-DSGC improves GCN accuracy significantly for low-degree nodes.
New approach uses unlabeled prior data to accelerate exploration in sparse reward tasks.
problem Sparse reward tasks in reinforcement learning.
method Learn reward model from online experience, label prior data, and use concurrently.
result Rapid exploration in challenging sparse-reward domains.
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, it is relatively insufficient to empower the discriminative ability of DGMs on making accurate predictions. This paper presents max-ma…
Improved negation detection in Dutch clinical texts using machine learning.
problem Extracting negation from clinical text for better model development.
method Comparison of rule-based and machine learning methods (biLSTM, RoBERTa).
result BiLSTM and RoBERTa models outperform rule-based method in F1 score, precision, and recall.
Model predicts respiratory insufficiency in ALS patients with high accuracy.
problem Lack of insight into risk of error and optimal time for non-invasive ventilation.
method Combines Conformal Prediction and mixture experts to predict respiratory insufficiency and optimal time.
result Near 80% of predictions correctly identified, with confidence measures.
We give an explicit algorithm and source code for combining alpha streams via bounded regression. In practical applications typically there is insufficient history to compute a sample covariance matrix (SCM) for a large number of alphas. To compute alpha allocation weights, one then resorts to (weighted) regression ove…
Music FaderNets learns high-level musical qualities from low-level attributes.
problem Learning high-level musical qualities from limited data and subjective labels.
method Model low-level attributes through feature disentanglement and latent regularization; infer high-level features from low-level representations using GM-VAEs.
result Model successfully learns intrinsic relationships between high-level features and low-level attributes with minimal labeled data.
MGM improves media profiling by integrating textual and structural features.
problem Evaluating the bias and factuality of news media from digital data.
method MediaGraphMind (MGM) framework using variational EM, integrating textual and structural features.
result Achieves new state-of-the-art results in media profiling.
A new decomposition explains over-parameterized models' counterintuitive behaviors.
problem Understanding predictive error in over-parameterized models.
method Introducing the Generalized Aliasing Decomposition (GAD) to explain predictive performance.
result The GAD decomposes predictive error into three parts: model insufficiency, data insufficiency, and generalized aliasing.
Improves unsupervised domain adaptation by mixing source and target domains.
problem Improves unsupervised domain adaptation by mixing source and target domains.
method Enforces training constraints across domains using mixup formulation and feature-level consistency regularizer.
result Significantly improves state-of-the-art performance on image classification and human activity recognition tasks.
Proposes Ada-Sit method for mortality prediction of rare diseases.
problem Data insufficiency and clinical diversity of rare diseases make mortality prediction hard.
method Initialization-sharing multi-task learning method (Ada-Sit) for fast adaptation to similar tasks.
result Experimental results show the proposed model is effective for mortality prediction of diverse rare diseases.
In our today's information society more and more data emerges, e.g.~in social networks, technical applications, or business applications. Companies try to commercialize these data using data mining or machine learning methods. For this purpose, the data are categorized or classified, but often at high (monetary or temp…
Two strategies for training network classifiers with feature heterogeneity.
problem Training network classifiers with agents having varying feature sizes and unreliable local decisions.
method Promotes global and local smoothing of classifier outputs.
result Output smoothing makes network classifier dynamics more complex, requiring regularization of parameters.
New method identifies common cause in causal insufficiency, revealing complex phase transitions.
problem Identifying common cause in causal insufficiency with observed joint probability.
method Generalized maximum likelihood method, closely related to maximum entropy principle.
result Identifies consistent common cause that aligns with the common cause principle.
New causal versions of MaxEnt and PIR avoid paradoxical probability updates.
problem Paradoxical probability updates in causal MaxEnt and PIR.
method Separate constraints into cause-specific and mechanism-specific restrictions.
result Causal MaxEnt avoids paradoxical updates and aligns with Information Geometric Causal Inference.
The paper proposes a variational autoencoder for discrete data analysis.
problem Sparse, high-dimensional, and overdispersed discrete data analysis.
method Variational autoencoder based on negative-binomial distribution.
result The proposed models achieve significantly better performance on text analysis, collaborative filtering, and multi-label learning compared to state-of-the-art baselines.
MIND models user interests with multiple vectors for better recommendation.
problem Insufficient representation of user interests in deep learning models.
method Multi-Interest Network with Dynamic routing (MIND) using capsule routing and label-aware attention.
result MIND achieves superior performance in recommendation compared to state-of-the-art methods.
CFM fee income is insufficient to hedge market risk, study finds.
problem Inefficiency of CFM fee income in hedging market risk.
method Analysis through continuous-time financial mathematics and multi-agent simulations.
result Fee income is insufficient to compensate for market risk.
Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: -Data insufficiency:Often in healthcare predictive modeling, the sample size is insufficient for deep learning methods to achieve satisfactory results. -Interpretation:The representations lear…
New findings suggest minimax optimality doesn't guarantee distribution learning for GANs.
problem Understanding when GANs can truly learn the underlying distribution.
method Using cryptographic assumptions and ReLU network generators, the paper shows that achieving minimax optimality is insufficient for distribution learning.
result Achieving minimax optimality is insufficient for distribution learning in the usual statistical sense.