While performance of many text classification tasks has been recently improved due to Pre-trained Language Models (PLMs), in this paper we show that they still suffer from a performance gap when the underlying distribution of topics changes. For example, a genre classifier trained on \textit{political} topics often fails when tested on documents about \textit{sport} or \textit{medicine}. In this work, we quantify this phenomenon empirically with a large corpus and a large set of topics. Consequently, we verify that domain transfer remains challenging both for classic PLMs, such as BERT, and for modern large models, such as GPT-3. We also suggest and successfully test a possible remedy: after augmenting the training dataset with topically-controlled synthetic texts, the F1 score improves by up to 50\% for some topics, nearing on-topic training results, while others show little to no improvement. While our empirical results focus on genre classification, our methodology is applicable to other classification tasks such as gender, authorship, or sentiment classification. The code and data to replicate the experiments are available at https://github.com/dminus1/genre
Multi-label document classification is a traditional task in NLP. Compared to single-label classification, each document can be assigned multiple classes. This problem is crucially important in various domains, such as tagging scientific articles. Documents are often structured into several sections such as abstract and title. Current approaches treat different sections equally for multi-label classification. We argue that this is not a realistic assumption, leading to sub-optimal results. Instead, we propose a new method called Learning Section Weights (LSW), leveraging the contribution of each distinct section for multi-label classification. Via multiple feed-forward layers, LSW learns to assign weights to each section of, and incorporate the weights in the prediction. We demonstrate our approach on scientific articles. Experimental results on public (arXiv) and private (Elsevier) datasets confirm the superiority of LSW, compared to state-of-the-art multi-label document classification methods. In particular, LSW achieves a 1.3% improvement in terms of macro averaged F1-score while it achieves 1.3% in terms of macro averaged recall on the publicly available arXiv dataset.
Quantum Transfer Learning (QTL) recently gained popularity as a hybrid quantum-classical approach for image classification tasks by efficiently combining the feature extraction capabilities of large Convolutional Neural Networks with the potential benefits of Quantum Machine Learning (QML). Existing approaches, however, only utilize gate-based Variational Quantum Circuits for the quantum part of these procedures. In this work we present an approach to employ Quantum Annealing (QA) in QTL-based image classification. Specifically, we propose using annealing-based Quantum Boltzmann Machines as part of a hybrid quantum-classical pipeline to learn the classification of real-world, large-scale data such as medical images through supervised training. We demonstrate our approach by applying it to the three-class COVID-CT-MD dataset, a collection of lung Computed Tomography (CT) scan slices. Using Simulated Annealing as a stand-in for actual QA, we compare our method to classical transfer learning, using a neural network of the same order of magnitude, to display its improved classification performance. We find that our approach consistently outperforms its classical baseline in terms of test accuracy and AUC-ROC-Score and needs less training epochs to do this.
The dissection of hyperspectral images into intrinsic components through hyperspectral intrinsic image decomposition (HIID) enhances the interpretability of hyperspectral data, providing a foundation for more accurate classification outcomes. However, the classification performance of HIID is constrained by the model's representational ability. To address this limitation, this study rethinks hyperspectral intrinsic image decomposition for classification tasks by introducing deep feature embedding. The proposed framework, HyperDID, incorporates the Environmental Feature Module (EFM) and Categorical Feature Module (CFM) to extract intrinsic features. Additionally, a Feature Discrimination Module (FDM) is introduced to separate environment-related and category-related features. Experimental results across three commonly used datasets validate the effectiveness of HyperDID in improving hyperspectral image classification performance. This novel approach holds promise for advancing the capabilities of hyperspectral image analysis by leveraging deep feature embedding principles. The implementation of the proposed method could be accessed soon at https://github.com/shendu-sw/HyperDID for the sake of reproducibility.
This paper addresses the challenge of point-supervised temporal action detection, in which only one frame per action instance is annotated in the training set. Self-training aims to provide supplementary supervision for the training process by generating pseudo-labels (action proposals) from a base model. However, most current methods generate action proposals by applying manually designed thresholds to action classification probabilities and treating adjacent snippets as independent entities. As a result, these methods struggle to generate complete action proposals, exhibit sensitivity to fluctuations in action classification scores, and generate redundant and overlapping action proposals. This paper proposes a novel framework termed ADM-Loc, which stands for Actionness Distribution Modeling for point-supervised action Localization. ADM-Loc generates action proposals by fitting a composite distribution, comprising both Gaussian and uniform distributions, to the action classification signals. This fitting process is tailored to each action class present in the video and is applied separately for each action instance, ensuring the distinctiveness of their distributions. ADM-Loc significantly enhances the alignment between the generated action proposals and ground-truth action instances and offers high-quality pseudo-labels for self-training. Moreover, to model action boundary snippets, it enforces consistency in action classification scores during training by employing Gaussian kernels, supervised with the proposed loss functions. ADM-Loc outperforms the state-of-the-art point-supervised methods on THUMOS14 and ActivityNet-v1.2 datasets.
Among the many tasks that Large Language Models (LLMs) have revolutionized is text classification. Current text classification paradigms, however, rely solely on the output of the final layer in the LLM, with the rich information contained in internal neurons largely untapped. In this study, we present SPIN: a model-agnostic framework that sparsifies and integrates internal neurons of intermediate layers of LLMs for text classification. Specifically, SPIN sparsifies internal neurons by linear probing-based salient neuron selection layer by layer, avoiding noise from unrelated neurons and ensuring efficiency. The cross-layer salient neurons are then integrated to serve as multi-layered features for the classification head. Extensive experimental results show our proposed SPIN significantly improves text classification accuracy, efficiency, and interpretability.
We conduct an extensive study on using near-term quantum computers for a task in the domain of computational biology. By constructing quantum models based on parameterised quantum circuits we perform sequence classification on a task relevant to the design of therapeutic proteins, and find competitive performance with classical baselines of similar scale. To study the effect of noise, we run some of the best-performing quantum models with favourable resource requirements on emulators of state-of-the-art noisy quantum processors. We then apply error mitigation methods to improve the signal. We further execute these quantum models on the Quantinuum H1-1 trapped-ion quantum processor and observe very close agreement with noiseless exact simulation. Finally, we perform feature attribution methods and find that the quantum models indeed identify sensible relationships, at least as well as the classical baselines. This work constitutes the first proof-of-concept application of near-term quantum computing to a task critical to the design of therapeutic proteins, opening the route toward larger-scale applications in this and related fields, in line with the hardware development roadmaps of near-term quantum technologies.
With increasing urbanization, transportation plays an increasingly critical role in city development. The number of studies on modeling, optimization, simulation, and data analysis of transportation systems is on the rise. Many of these studies utilize transportation test networks to represent real-world transportation systems in urban areas, examining the efficacy of their proposed approaches. Each of these networks exhibits unique characteristics in their topology, making their applications distinct for various study objectives. Despite their widespread use in research, there is a lack of comprehensive study addressing the classification of these networks based on their topological characteristics. This study aims to fill this gap by employing unsupervised learning methods, particularly clustering. We present a comprehensive framework for evaluating various topological network characteristics. Additionally, we employ two dimensionality reduction techniques, namely Principal Component Analysis (PCA) and Isometric Feature Mapping (ISOMAP), to reduce overlaps of highly correlated features and enhance the interpretability of the subsequent classification results. We then utilize two clustering algorithms, K-means and HDBSCAN, to classify 14 transportation networks. The PCA method, followed by the K-means clustering approach, outperforms other alternatives with a Silhouette score of $0.510$, enabling the classification of transportation networks into five clusters. We also provide a detailed discussion on the resulting classification.
Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset. Most existing dataset pruning methods rely on snapshot-based criteria to identify representative samples, often resulting in poor generalization across various pruning and cross-architecture scenarios. Recent studies have addressed this issue by expanding the scope of training dynamics considered, including factors such as forgetting event and probability change, typically using an averaging approach. However, these works struggle to integrate a broader range of training dynamics without overlooking well-generalized samples, which may not be sufficiently highlighted in an averaging manner. In this study, we propose a novel dataset pruning method termed as Temporal Dual-Depth Scoring (TDDS), to tackle this problem. TDDS utilizes a dual-depth strategy to achieve a balance between incorporating extensive training dynamics and identifying representative samples for dataset pruning. In the first depth, we estimate the series of each sample's individual contributions spanning the training progress, ensuring comprehensive integration of training dynamics. In the second depth, we focus on the variability of the sample-wise contributions identified in the first depth to highlight well-generalized samples. Extensive experiments conducted on CIFAR and ImageNet datasets verify the superiority of TDDS over previous SOTA methods. Specifically on CIFAR-100, our method achieves 54.51% accuracy with only 10% training data, surpassing random selection by 7.83% and other comparison methods by at least 12.69%.
Coral reefs are vital for marine biodiversity, coastal protection, and supporting human livelihoods globally. However, they are increasingly threatened by mass bleaching events, pollution, and unsustainable practices with the advent of climate change. Monitoring the health of these ecosystems is crucial for effective restoration and management. Current methods for creating benthic composition maps often compromise between spatial coverage and resolution. In this paper, we introduce BenthIQ, a multi-label semantic segmentation network designed for high-precision classification of underwater substrates, including live coral, algae, rock, and sand. Although commonly deployed CNNs are limited in learning long-range semantic information, transformer-based models have recently achieved state-of-the-art performance in vision tasks such as object detection and image classification. We integrate the hierarchical Swin Transformer as the backbone of a U-shaped encoder-decoder architecture for local-global semantic feature learning. Using a real-world case study in French Polynesia, we demonstrate that our approach outperforms traditional CNN and attention-based models on pixel-wise classification of shallow reef imagery.
Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural network models usually excel in closed-set classification while performs poorly in rejecting OOD inputs. To tackle this problem, numerous methods have been designed to perform open set recognition (OSR) or OOD rejection/detection tasks. Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes. In this paper, we attempt to build a unified framework for building open set classifiers for both classification and OOD rejection. We formulate the open set recognition of $ K $-known-class as a $ (K+1) $-class classification problem with model trained on known-class samples only. By decomposing the $ K $-class problem into $ K $ one-versus-all (OVA) binary classification tasks and binding some parameters, we show that combining the scores of OVA classifiers can give $ (K+1) $-class posterior probabilities, which enables classification and OOD rejection in a unified framework. To maintain the closed-set classification accuracy of the OVA trained classifier, we propose a hybrid training strategy combining OVA loss and multi-class cross-entropy loss. We implement the OVA framework and hybrid training strategy on the recently proposed convolutional prototype network and prototype classifier on vision transformer (ViT) backbone. Experiments on popular OSR and OOD detection datasets demonstrate that the proposed framework, using a single multi-class classifier, yields competitive performance in closed-set classification, OOD detection, and misclassification detection.
In this work, we evaluate the energy usage of fully embedded medical diagnosis aids based on both segmentation and classification of medical images implemented on Edge TPU and embedded GPU processors. We use glaucoma diagnosis based on color fundus images as an example to show the possibility of performing segmentation and classification in real time on embedded boards and to highlight the different energy requirements of the studied implementations. Several other works develop the use of segmentation and feature extraction techniques to detect glaucoma, among many other pathologies, with deep neural networks. Memory limitations and low processing capabilities of embedded accelerated systems (EAS) limit their use for deep network-based system training. However, including specific acceleration hardware, such as NVIDIA's Maxwell GPU or Google's Edge TPU, enables them to perform inferences using complex pre-trained networks in very reasonable times. In this study, we evaluate the timing and energy performance of two EAS equipped with Machine Learning (ML) accelerators executing an example diagnostic tool developed in a previous work. For optic disc (OD) and cup (OC) segmentation, the obtained prediction times per image are under 29 and 43 ms using Edge TPUs and Maxwell GPUs, respectively. Prediction times for the classification subsystem are lower than 10 and 14 ms for Edge TPUs and Maxwell GPUs, respectively. Regarding energy usage, in approximate terms, for OD segmentation Edge TPUs and Maxwell GPUs use 38 and 190 mJ per image, respectively. For fundus classification, Edge TPUs and Maxwell GPUs use 45 and 70 mJ, respectively.
Unlike the more commonly analyzed ECG or PPG data for activity classification, heart rate time series data is less detailed, often noisier and can contain missing data points. Using the BigIdeasLab_STEP dataset, which includes heart rate time series annotated with specific tasks performed by individuals, we sought to determine if general classification was achievable. Our analyses showed that the accuracy is sensitive to the choice of window/stride size. Moreover, we found variable classification performances between subjects due to differences in the physical structure of their hearts. Various techniques were used to minimize this variability. First of all, normalization proved to be a crucial step and significantly improved the performance. Secondly, grouping subjects and performing classification inside a group helped to improve performance and decrease inter-subject variability. Finally, we show that including handcrafted features as input to a deep learning (DL) network improves the classification performance further. Together, these findings indicate that heart rate time series can be utilized for classification tasks like predicting activity. However, normalization or grouping techniques need to be chosen carefully to minimize the issue of subject variability.
While graph neural networks have achieved state-of-the-art performances in many real-world tasks including graph classification and node classification, recent works have demonstrated they are also extremely vulnerable to adversarial attacks. Most previous works have focused on attacking node classification networks under impractical white-box scenarios. In this work, we will propose a non-targeted Hard Label Black Box Node Injection Attack on Graph Neural Networks, which to the best of our knowledge, is the first of its kind. Under this setting, more real world tasks can be studied because our attack assumes no prior knowledge about (1): the model architecture of the GNN we are attacking; (2): the model's gradients; (3): the output logits of the target GNN model. Our attack is based on an existing edge perturbation attack, from which we restrict the optimization process to formulate a node injection attack. In the work, we will evaluate the performance of the attack using three datasets, COIL-DEL, IMDB-BINARY, and NCI1.
Sound Source Localization (SSL) involves estimating the Direction of Arrival (DOA) of sound sources. Since the DOA estimation output space is continuous, regression might be more suitable for DOA, offering higher precision. However, in practice, classification often outperforms regression, exhibiting greater robustness to interference. Conversely, classification's drawback is inherent quantization error. Within the classification paradigm, the DOA output space is discretized into intervals, each treated as a class. These classes show strong inter-class correlations, being inherently ordered, with higher similarity as intervals grow closer. Nevertheless, this has not been fully exploited. To address this, we propose an Unbiased Label Distribution (ULD) to eliminate quantization error in training targets. Furthermore, we tailor two loss functions for the soft label family: Negative Log Absolute Error (NLAE) and Mean Squared Error without activation (MSE(wo)). Finally, we introduce Weighted Adjacent Decoding (WAD) to overcome quantization error during model prediction decoding. Experimental results demonstrate our approach surpasses classification quantization limits, achieving state-of-the-art performance. Our code and supplementary materials are available at https://github.com/linfeng-feng/ULD.
Formally verifying audio classification systems is essential to ensure accurate signal classification across real-world applications like surveillance, automotive voice commands, and multimedia content management, preventing potential errors with serious consequences. Drawing from recent research, this study advances the utilization of star-set-based formal verification, extended through reachability analysis, tailored explicitly for Long Short-Term Memory architectures and their Convolutional variations within the audio classification domain. By conceptualizing the classification process as a sequence of set operations, the star set-based reachability approach streamlines the exploration of potential operational states attainable by the system. The paper serves as an encompassing case study, validating and verifying sequence audio classification analytics within real-world contexts. It accentuates the necessity for robustness verification to ensure precise and dependable predictions, particularly in light of the impact of noise on the accuracy of output classifications.
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g. women vs. men) remains an open challenge. This paper presents a novel method for mitigating biases in neural text classification, agnostic to the model architecture. Considering the difficulty to distinguish fair from unfair information in a text encoder, we take inspiration from adversarial training to induce Wasserstein independence between representations learned to predict our target label and the ones learned to predict some sensitive attribute. Our approach provides two significant advantages. Firstly, it does not require annotations of sensitive attributes in both testing and training data. This is more suitable for real-life scenarios compared to existing methods that require annotations of sensitive attributes at train time. Second, our approach exhibits a comparable or better fairness-accuracy trade-off compared to existing methods.
Schizophrenia is a complicated mental illness characterized by a broad spectrum of symptoms affecting cognition, behavior, and emotion. The task of identifying reliable biomarkers to classify Schizophrenia accurately continues to be a challenge in the field of psychiatry. We investigate the temporal patterns within the motor activity data as a potential key to enhancing the categorization of individuals with Schizophrenia, using the dataset having motor activity recordings of 22 Schizophrenia patients and 32 control subjects. The dataset contains per-minute motor activity measurements collected for an average of 12.7 days in a row for each participant. We dissect each day into segments (Twelve, Eight, six, four, three, and two parts) and evaluate their impact on classification. We employ sixteen statistical features within these temporal segments and train them on Seven machine learning models to get deeper insights. LightGBM model outperforms the other six models. Our results indicate that the temporal segmentation significantly improves the classification, with AUC-ROC = 0.93, F1 score = 0.84( LightGBM- without any segmentation) and AUC-ROC = 0.98, F1 score = 0.93( LightGBM- with segmentation). Distinguishing between diurnal and nocturnal segments amplifies the differences between Schizophrenia patients and controls. However, further subdivisions into smaller time segments do not affect the AUC- ROC significantly. Morning, afternoon, evening, and night partitioning gives similar classification performance to day-night partitioning. These findings are valuable as they indicate that extensive temporal classification beyond distinguishing between day and night does not yield substantial results, offering an efficient approach for further classification, early diagnosis, and monitoring of Schizophrenia.
Advancing loss function design is pivotal for optimizing neural network training and performance. This work introduces Random Linear Projections (RLP) loss, a novel approach that enhances training efficiency by leveraging geometric relationships within the data. Distinct from traditional loss functions that target minimizing pointwise errors, RLP loss operates by minimizing the distance between sets of hyperplanes connecting fixed-size subsets of feature-prediction pairs and feature-label pairs. Our empirical evaluations, conducted across benchmark datasets and synthetic examples, demonstrate that neural networks trained with RLP loss outperform those trained with traditional loss functions, achieving improved performance with fewer data samples, and exhibiting greater robustness to additive noise. We provide theoretical analysis supporting our empirical findings.
We propose a method for the classification of objects that are structured as random trees. Our aim is to model a distribution over the node label assignments in settings where the tree data structure is associated with node attributes (typically high dimensional embeddings). The tree topology is not predetermined and none of the label assignments are present during inference. Other methods that produce a distribution over node label assignment in trees (or more generally in graphs) either assume conditional independence of the label assignment, operate on a fixed graph topology, or require part of the node labels to be observed. Our method defines a Markov Network with the corresponding topology of the random tree and an associated Gibbs distribution. We parameterize the Gibbs distribution with a Graph Neural Network that operates on the random tree and the node embeddings. This allows us to estimate the likelihood of node assignments for a given random tree and use MCMC to sample from the distribution of node assignments. We evaluate our method on the tasks of node classification in trees on the Stanford Sentiment Treebank dataset. Our method outperforms the baselines on this dataset, demonstrating its effectiveness for modeling joint distributions of node labels in random trees.