The paper supports task classification from eye movements, achieving 95.4% accuracy.
problem Decoding the observer's task from eye movements.
method Exploratory analysis, feature projection, feature elimination, SVM and Ada Boosting classifier training.
result Achieved 95.4% accuracy in task classification.
Language models help text classification tasks by predicting next words.
problem Lack of theoretical understanding of why language models perform well on downstream tasks.
method Mathematical study of the connection between next word prediction and text classification, formalizing it and quantifying the benefit.
result Language models that are ε-optimal in cross-entropy learn features that can solve classification tasks with linear approximation.
DEN learns diverse tasks to generalize to unseen tasks.
problem Generalization from a diverse set of classification tasks with limited data.
method Three-block architecture: covariate transformation, distribution embedding, and classification.
result DEN outperforms existing methods in various synthetic and real tasks.
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new clas…
MODWST improves classification tasks with wavelet scattering.
problem Signal classification challenges.
method Combines MODWT and WST for feature extraction.
result MODWST outperforms CNNs in limited data scenarios.
Detects out-of-domain cases with limited training data.
problem Detecting out-of-domain cases with insufficient in-domain training data.
method Proposes an OOD-resistant Prototypical Network.
result Outperforms state-of-the-art methods in zero-shot OOD detection.
Estimates task difficulty and transferability without trained models.
problem Estimating the difficulty and transferability of supervised classification tasks.
method Information theoretic approach using conditional entropy between training labels.
result Hardness and transferability estimates correlate with empirical values.
A new method classifies multiple correlated data streams simultaneously.
problem Classifying multiple correlated data streams in practical scenarios.
method Double-Coupling Support Vector Machines (DC-SVM) considers both internal and external correlations.
result The proposed method outperforms traditional methods on artificial and real-world data streams.
Proposes a method to evaluate meta-learning performance based on task similarity.
problem Meta-learning performance evaluation ignores task similarity, leading to biased results.
method Generative approach using Latent Dirichlet Allocation to analyze task similarity.
result The proposed method provides an insightful evaluation of meta-learning algorithms, matching common intuition.
Task shift from classification to regression is possible in overparameterized linear models with limited additional data.
problem Transferability of latent knowledge from classification to regression in overparameterized linear models.
method Investigation of task shift in overparameterized linear regression, zero-shot and few-shot cases, with a focus on minimum-norm interpolation.
result Minimum-norm interpolators can transfer latent knowledge from classification to regression with limited additional data.
QUACKIE creates a new benchmark for NLP interpretability.
problem Evaluating NLP interpretability methods is challenging due to biased ground truths.
method Formulated a custom classification task from question-answering datasets, generating unbiased ground truths.
result Demonstrated the effectiveness of current interpretability methods on the new benchmark.
A new optimizer, Grad-Avg, converges faster than SGD and improves classification task performance.
problem Optimizing error functions in regression and classification tasks.
method Grad-Avg optimizer based on gradient averaging, with mathematical convergence proof and parameter scaling for classification.
result Grad-Avg converges faster than other optimizers for classification tasks on benchmark datasets.
A new framework integrates classification and regression tasks in multi-task learning.
problem Jointly solving classification and regression tasks in multi-task scenarios.
method Two-Stage Learning-to-Defer (L2D) framework with a unified deferral mechanism.
result Unified deferral mechanism ensures convergence to the Bayes-optimal rejector.
Survey tackles continual learning in classification tasks to prevent forgetting.
problem Prevent catastrophic forgetting in neural networks across multiple tasks.
method Taxonomy, stability-plasticity trade-off framework, comprehensive comparison of methods.
result Empirical evaluation of continual learning methods on various benchmarks.
Classification of audio samples is an important part of many auditory systems. Deep learning models based on the Convolutional and the Recurrent layers are state-of-the-art in many such tasks. In this paper, we approach audio classification tasks using capsule networks trained by recently proposed dynamic routing-by-ag…
Meta-learning strategy improves few-shot classification performance.
problem Few-shot classification with deep neural networks struggles when labeled samples are limited.
method Proposes an easy-to-hard expert meta-training strategy to arrange training tasks based on task hardness.
result Meta-learners achieve better results with the proposed expert training strategy.
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural languag…
Study improves radio show segmentation using audio embeddings.
problem Automated segmentation of radio shows.
method Created audio embeddings from multi-class classification tasks on different datasets, evaluated performance against text-only baseline.
result Audio embeddings from non-speech sound event classification significantly outperformed text-only baseline by 32.3% in F1-measure.
A new framework improves few-shot classification by learning to generalize to unseen classes.
problem Training metric-based meta-learning approaches for few-shot classification often fails to generalize to unseen classes.
method Proposes a bilevel optimization framework to explicitly constrain meta-training to reduce unseen classification error.
result Significantly improves performance on unseen classes compared to episodic training.
Improves deep learning robustness by considering task and model.
problem Adversarial attacks on deep learning systems.
method Binary and interval label encoding strategy to redefine classification tasks and design corresponding loss functions.
result Our method enhances robustness without sacrificing accuracy.
Develops methods to control risk in ordinal classification tasks.
problem Controlling risk in ordinal classification tasks.
method Formulated ordinal classification in conformal risk control framework, proposed loss functions and algorithms.
result Demonstrated effectiveness and analyzed differences in risk control methods.
The study examines generalization bounds for regression and classification tasks on adaptive input domains.
problem Understanding the generalization error in adaptive input domains for regression and classification.
method The analysis considers regression and classification separately, using Lipschitz continuity and 2-norm/0/1 loss for measurement. It also highlights the polynomial relationship between generalization bounds and network parameters.
result Generalization bounds for regression and classification are inversely proportional to a polynomial of the number of parameters, emphasizing the advantages of over-parameterized networks.
The paper identifies conditions for trend reversal in classification tasks.
problem Trend reversal in classification scores and dataset values.
method Algebraic conditions and numerical results for ridge regression.
result Existence of pathological regularization regimes for certain dataset conditions.
Paper tackles counterfactual sentence detection and evaluation.
problem Detect and evaluate counterfactual sentences in natural language.
method Used a BERT base model for classification and a hybrid BERT Multi-Layer Perceptron for sequence identification. Introduced cascaded linear inputs to improve performance.
result Achieved an F1 score of 85.00% in Task 1 and 83.90% in Task 2.
Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification a…
Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain performance on previously learned tasks when tasks are presented one at a time. This pro…
Develops a new minimax probability machine for imbalanced classification tasks.
problem Imbalanced classification tasks with non-decomposable performance measures.
method Derives an equivalent form of the MPMF model for solving linear and nonlinear classifiers.
result Demonstrates the effectiveness of the new model on real-world datasets.
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.
We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence cl…
Unified approach to non-standard classification tasks.
problem Non-standard classification tasks like semi-supervised, positive-unlabelled, multi-positive-unlabelled and noisy-label learning.
method Probabilistic, unified approach training a classifier to predict label-distributions, then inferring class-distributions.
result Unified model for various non-standard classification tasks.
BERT improves fine-grained sentiment classification.
problem Fine-grained sentiment classification of text.
method Used BERT for fine-grained sentiment classification.
result BERT outperforms other models for fine-grained sentiment classification.
Keyphrase boundary classification (KBC) is the task of detecting keyphrases in scientific articles and labelling them with respect to predefined types. Although important in practice, this task is so far underexplored, partly due to the lack of labelled data. To overcome this, we explore several auxiliary tasks, includ…
Defines a similarity measure for classification distributions.
problem Measuring similarity between classification distributions.
method Proposes task similarity, a novel measure quantifying performance of source distributions on target distributions.
result Empirical task similarity correlates with transfer efficiency and semantic similarity of source distributions.
This paper describes the participation of Amobee in the shared sentiment analysis task at SemEval 2018. We participated in all the English sub-tasks and the Spanish valence tasks. Our system consists of three parts: training task-specific word embeddings, training a model consisting of gated-recurrent-units (GRU) with …
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.
PosCal training improves classification models by calibrating posterior probabilities.
problem Poorly calibrated posterior probabilities in classification models.
method End-to-end training procedure that directly optimizes the objective while minimizing the difference between predicted and empirical posterior probabilities.
result PosCal training achieves about 2.5% task performance gain and 16.1% calibration error reduction.
Study shows topological features improve time series classification.
problem Classifying stochastic processes with varying noise and sampling.
method Topological data analysis features compared to statistical and raw features.
result Topological features lead to better classification performance.
Electrocardiogram (ECG) can be reliably used as a measure to monitor the functionality of the cardiovascular system. Recently, there has been a great attention towards accurate categorization of heartbeats. While there are many commonalities between different ECG conditions, the focus of most studies has been classifyi…
A multi-task model tackles citation purpose classification with limited data.
problem Classifying citations based on their purpose is challenging due to limited labeled data and subjectivity.
method Combines linguistic features, TF-IDF, and an LSTM-with-attention model for multi-task learning.
result Improves classification accuracy compared to single-task models.
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.
Improved VAE representations lead to better image classification.
problem VAE representations are inferior to non-latent models for image classification.
method Used a decoder that prefers local features, improving global feature capture in latent variables.
result Significant improvement in downstream semantic classification tasks.
ADReSS Challenge at INTERSPEECH 2020 benchmarks speech recognition for Alzheimer's dementia.
problem Automated recognition of Alzheimer's dementia from spontaneous speech.
method Provides a benchmark speech dataset, defines two tasks (classification and regression), and presents baseline models.
result Demonstrates the feasibility of automated speech recognition for Alzheimer's dementia.
We propose a new family of fairness definitions for classification problems that combine some of the best properties of both statistical and individual notions of fairness. We posit not only a distribution over individuals, but also a distribution over (or collection of) classification tasks. We then ask that standard …
Dictionary learning algorithms have been successfully used in both reconstructive and discriminative tasks, where the input signal is represented by a linear combination of a few dictionary atoms. While these methods are usually developed under ℓ1 sparsity constrain (prior) in the input domain, recent studies hav…
Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL considerably outperforms the traditional Single task learning (STL) in terms of…
Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approach, Bi-stream Emotion Attribution-Classification Network (BEAC-Net), to solve three related emotion …
Motivation: Tumor classification using Imaging Mass Spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Deep learning offers an approach to learn featu…
Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during …