Every publicly traded company in the US is required to file an annual 10-K financial report, which contains a wealth of information about the company. In this paper, we propose an explainable deep-learning model, called FinBERT-XRC, that takes a 10-K report as input, and automatically assesses the post-event return volatility risk of its associated company. In contrast to previous systems, our proposed model simultaneously offers explanations of its classification decision at three different levels: the word, sentence, and corpus levels. By doing so, our model provides a comprehensive interpretation of its prediction to end users. This is particularly important in financial domains, where the transparency and accountability of algorithmic predictions play a vital role in their application to decision-making processes. Aside from its novel interpretability, our model surpasses the state of the art in predictive accuracy in experiments on a large real-world dataset of 10-K reports spanning six years.
Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language Models (LLMs) to generate text concepts and employing Vision Language Models (VLMs) to score these concepts for CBM training. However, it is desired to build CBMs with concepts defined by human experts rather than LLM-generated ones to make them more trustworthy. In this work, we closely examine the faithfulness of VLM concept scores for such expert-defined concepts in domains like fine-grained bird species and animal classification. Our investigations reveal that VLMs like CLIP often struggle to correctly associate a concept with the corresponding visual input, despite achieving a high classification performance. This misalignment renders the resulting models difficult to interpret and less reliable. To address this issue, we propose a novel Contrastive Semi-Supervised (CSS) learning method that leverages a few labeled concept samples to activate truthful visual concepts and improve concept alignment in the CLIP model. Extensive experiments on three benchmark datasets demonstrate that our method significantly enhances both concept (+29.95) and classification (+3.84) accuracies yet requires only a fraction of human-annotated concept labels. To further improve the classification performance, we introduce a class-level intervention procedure for fine-grained classification problems that identifies the confounding classes and intervenes in their concept space to reduce errors.
Deep learning models are often unaware of the inherent constraints of the task they are applied to. However, many downstream tasks require logical consistency. For ontology classification tasks, such constraints include subsumption and disjointness relations between classes. In order to increase the consistency of deep learning models, we propose a fuzzy loss that combines label-based loss with terms penalising subsumption- or disjointness-violations. Our evaluation on the ChEBI ontology shows that the fuzzy loss is able to decrease the number of consistency violations by several orders of magnitude without decreasing the classification performance. In addition, we use the fuzzy loss for unsupervised learning. We show that this can further improve consistency on data from a
Brain-Computer Interfaces (BCIs) rely on accurately decoding electroencephalography (EEG) motor imagery (MI) signals for effective device control. Graph Neural Networks (GNNs) outperform Convolutional Neural Networks (CNNs) in this regard, by leveraging the spatial relationships between EEG electrodes through adjacency matrices. The EEG_GLT-Net framework, featuring the state-of-the-art EEG_GLT adjacency matrix method, has notably enhanced EEG MI signal classification, evidenced by an average accuracy of 83.95% across 20 subjects on the PhysioNet dataset. This significantly exceeds the 76.10% accuracy rate achieved using the Pearson Correlation Coefficient (PCC) method within the same framework. In this research, we advance the field by applying a Reinforcement Learning (RL) approach to the classification of EEG MI signals. Our innovative method empowers the RL agent, enabling not only the classification of EEG MI data points with higher accuracy, but effective identification of EEG MI data points that are less distinct. We present the EEG_RL-Net, an enhancement of the EEG_GLT-Net framework, which incorporates the trained EEG GCN Block from EEG_GLT-Net at an adjacency matrix density of 13.39% alongside the RL-centric Dueling Deep Q Network (Dueling DQN) block. The EEG_RL-Net model showcases exceptional classification performance, achieving an unprecedented average accuracy of 96.40% across 20 subjects within 25 milliseconds. This model illustrates the transformative effect of the RL in EEG MI time point classification.
Recently, there has been a significant focus on exploring the theoretical aspects of deep learning, especially regarding its performance in classification tasks. Bayesian deep learning has emerged as a unified probabilistic framework, seeking to integrate deep learning with Bayesian methodologies seamlessly. However, there exists a gap in the theoretical understanding of Bayesian approaches in deep learning for classification. This study presents an attempt to bridge that gap. By leveraging PAC-Bayes bounds techniques, we present theoretical results on the prediction or misclassification error of a probabilistic approach utilizing Spike-and-Slab priors for sparse deep learning in classification. We establish non-asymptotic results for the prediction error. Additionally, we demonstrate that, by considering different architectures, our results can achieve minimax optimal rates in both low and high-dimensional settings, up to a logarithmic factor. Moreover, our additional logarithmic term yields slight improvements over previous works. Additionally, we propose and analyze an automated model selection approach aimed at optimally choosing a network architecture with guaranteed optimality.
Bayesian few-shot classification has been a focal point in the field of few-shot learning. This paper seamlessly integrates mirror descent-based variational inference into Gaussian process-based few-shot classification, addressing the challenge of non-conjugate inference. By leveraging non-Euclidean geometry, mirror descent achieves accelerated convergence by providing the steepest descent direction along the corresponding manifold. It also exhibits the parameterization invariance property concerning the variational distribution. Experimental results demonstrate competitive classification accuracy, improved uncertainty quantification, and faster convergence compared to baseline models. Additionally, we investigate the impact of hyperparameters and components. Code is publicly available at https://github.com/keanson/MD-BSFC.
Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized. Improving DNN calibration without comprising on model accuracy is of extreme importance and interest in safety critical applications such as in the health-care sector. In this work, we show that decoupling the training of feature extraction layers and classification layers in over-parametrized DNN architectures such as Wide Residual Networks (WRN) and Visual Transformers (ViT) significantly improves model calibration whilst retaining accuracy, and at a low training cost. In addition, we show that placing a Gaussian prior on the last hidden layer outputs of a DNN, and training the model variationally in the classification training stage, even further improves calibration. We illustrate these methods improve calibration across ViT and WRN architectures for several image classification benchmark datasets.
As a natural extension to the standard conformal prediction method, several conformal risk control methods have been recently developed and applied to various learning problems. In this work, we seek to control the conformal risk in expectation for ordinal classification tasks, which have broad applications to many real problems. For this purpose, we firstly formulated the ordinal classification task in the conformal risk control framework, and provided theoretic risk bounds of the risk control method. Then we proposed two types of loss functions specially designed for ordinal classification tasks, and developed corresponding algorithms to determine the prediction set for each case to control their risks at a desired level. We demonstrated the effectiveness of our proposed methods, and analyzed the difference between the two types of risks on three different datasets, including a simulated dataset, the UTKFace dataset and the diabetic retinopathy detection dataset.
Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small datasets due to limited access to quantum hardware and computationally expensive simulations. To that end, we implemented a Jax-based framework that enables the simulation of medium-sized qubit architectures with significant improvements in wall-clock time over current software offerings. We evaluated the performance of our Jax-based framework in terms of efficiency and performance for hybrid quantum transfer learning for long-tailed classification across 8, 14, and 19 disease labels using large-scale CXR datasets. The Jax-based framework resulted in up to a 58% and 95% speed-up compared to PyTorch and TensorFlow implementations, respectively. However, compared to CML, QML demonstrated slower convergence and an average AUROC of 0.70, 0.73, and 0.74 for the classification of 8, 14, and 19 CXR disease labels. In comparison, the CML models had an average AUROC of 0.77, 0.78, and 0.80 respectively. In conclusion, our work presents an accessible implementation of hybrid quantum transfer learning for long-tailed CXR classification with a computationally efficient Jax-based framework.
Deep neural networks, including Convolutional Neural Networks (CNNs) and Visual Transformers (ViT), have achieved stunning success in medical image domain. We study thorax disease classification in this paper. Effective extraction of features for the disease areas is crucial for disease classification on radiographic images. While various neural architectures and training techniques, such as self-supervised learning with contrastive/restorative learning, have been employed for disease classification on radiographic images, there are no principled methods which can effectively reduce the adverse effect of noise and background, or non-disease areas, on the radiographic images for disease classification. To address this challenge, we propose a novel Low-Rank Feature Learning (LRFL) method in this paper, which is universally applicable to the training of all neural networks. The LRFL method is both empirically motivated by the low frequency property observed on all the medical datasets in this paper, and theoretically motivated by our sharp generalization bound for neural networks with low-rank features. In the empirical study, using a neural network such as a ViT or a CNN pre-trained on unlabeled chest X-rays by Masked Autoencoders (MAE), our novel LRFL method is applied on the pre-trained neural network and demonstrate better classification results in terms of both multiclass area under the receiver operating curve (mAUC) and classification accuracy.
This paper describes our participation in Task 3 and Task 5 of the #SMM4H (Social Media Mining for Health) 2024 Workshop, explicitly targeting the classification challenges within tweet data. Task 3 is a multi-class classification task centered on tweets discussing the impact of outdoor environments on symptoms of social anxiety. Task 5 involves a binary classification task focusing on tweets reporting medical disorders in children. We applied transfer learning from pre-trained encoder-decoder models such as BART-base and T5-small to identify the labels of a set of given tweets. We also presented some data augmentation methods to see their impact on the model performance. Finally, the systems obtained the best F1 score of 0.627 in Task 3 and the best F1 score of 0.841 in Task 5.
Subdata selection is a study of methods that select a small representative sample of the big data, the analysis of which is fast and statistically efficient. The existing subdata selection methods assume that the big data can be reasonably modeled using an underlying model, such as a (multinomial) logistic regression for classification problems. These methods work extremely well when the underlying modeling assumption is correct but often yield poor results otherwise. In this paper, we propose a model-free subdata selection method for classification problems, and the resulting subdata is called PED subdata. The PED subdata uses decision trees to find a partition of the data, followed by selecting an appropriate sample from each component of the partition. Random forests are used for analyzing the selected subdata. Our method can be employed for a general number of classes in the response and for both categorical and continuous predictors. We show analytically that the PED subdata results in a smaller Gini than a uniform subdata. Further, we demonstrate that the PED subdata has higher classification accuracy than other competing methods through extensive simulated and real datasets.
We introduce a class of neural controlled differential equation inspired by quantum mechanics. Neural quantum controlled differential equations (NQDEs) model the dynamics by analogue of the Schr\"{o}dinger equation. Specifically, the hidden state represents the wave function, and its collapse leads to an interpretation of the classification probability. We implement and compare the results of four variants of NQDEs on a toy spiral classification problem.
Brain responses related to working memory originate from distinct brain areas and oscillate at different frequencies. EEG signals with high temporal correlation can effectively capture these responses. Therefore, estimating the functional connectivity of EEG for working memory protocols in different frequency bands plays a significant role in analyzing the brain dynamics with increasing memory and cognitive loads, which remains largely unexplored. The present study introduces a Bayesian structure learning algorithm to learn the functional connectivity of EEG in sensor space. Next, the functional connectivity graphs are taken as input to the graph convolutional network to classify the working memory loads. The intrasubject (subject-specific) classification performed on 154 subjects for six different verbal working memory loads produced the highest classification accuracy of 96% and average classification accuracy of 89%, outperforming state-of-the-art classification models proposed in the literature. Furthermore, the proposed Bayesian structure learning algorithm is compared with state-of-the-art functional connectivity estimation methods through intersubject and intrasubject statistical analysis of variance. The results also show that the alpha and theta bands have better classification accuracy than the beta band.
In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in the real world. For richer classes of the similarity, we propose the use of weighted point clouds, namely, sets of pairs of weight and vector, as representations of instances. In this work, we theoretically show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP, which we call symmetric InfoNCE. We clarify that the optimal similarity that minimizes symmetric InfoNCE is the pointwise mutual information, and show an upper bound of excess risk on downstream classification tasks of representations that achieve the optimal similarity. In addition, we show that our proposed similarity based on weighted point clouds consistently achieves the optimal similarity. To verify the effectiveness of our proposed method, we demonstrate pretraining of text-image representation models and classification tasks on common benchmarks.
Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large amounts of personal data, their usage can pose a threat to user privacy and weaken the bonds of trust between humans and AI services. In response to these concerns, legislation advocating ``the right to be forgotten" has recently been proposed, allowing users to request the removal of private information from computer systems and neural network models. A novel approach, known as machine unlearning, has emerged to make AI models forget about a particular class of data. In our research, we explore machine unlearning for document classification problems, representing, to the best of our knowledge, the first investigation into this area. Specifically, we consider a realistic scenario where a remote server houses a well-trained model and possesses only a small portion of training data. This setup is designed for efficient forgetting manipulation. This work represents a pioneering step towards the development of machine unlearning methods aimed at addressing privacy concerns in document analysis applications. Our code is publicly available at \url{https://github.com/leitro/MachineUnlearning-DocClassification}.
One of the prime problems of computer science and machine learning is to extract information efficiently from large-scale, heterogeneous data. Text data, with its syntax, semantics, and even hidden information content, possesses an exceptional place among the data types in concern. The processing of the text data requires embedding, a method of translating the content of the text to numeric vectors. A correct embedding algorithm is the starting point for obtaining the full information content of the text data. In this work, a new text embedding approach, namely the Guided Transition Probability Matrix (GTPM) model is proposed. The model uses the graph structure of sentences to capture different types of information from text data, such as syntactic, semantic, and hidden content. Using random walks on a weighted word graph, GTPM calculates transition probabilities to derive text embedding vectors. The proposed method is tested with real-world data sets and eight well-known and successful embedding algorithms. GTPM shows significantly better classification performance for binary and multi-class datasets than well-known algorithms. Additionally, the proposed method demonstrates superior robustness, maintaining performance with limited (only $10\%$) training data, showing an $8\%$ decline compared to $15-20\%$ for baseline methods.
Similar to humans, animals make extensive use of verbal and non-verbal forms of communication, including a large range of audio signals. In this paper, we address dog vocalizations and explore the use of self-supervised speech representation models pre-trained on human speech to address dog bark classification tasks that find parallels in human-centered tasks in speech recognition. We specifically address four tasks: dog recognition, breed identification, gender classification, and context grounding. We show that using speech embedding representations significantly improves over simpler classification baselines. Further, we also find that models pre-trained on large human speech acoustics can provide additional performance boosts on several tasks.
Forensic authorship profiling uses linguistic markers to infer characteristics about an author of a text. This task is paralleled in dialect classification, where a prediction is made about the linguistic variety of a text based on the text itself. While there have been significant advances in recent years in variety classification, forensic linguistics rarely relies on these approaches due to their lack of transparency, among other reasons. In this paper we therefore explore the explainability of machine learning approaches considering the forensic context. We focus on variety classification as a means of geolinguistic profiling of unknown texts based on social media data from the German-speaking area. For this, we identify the lexical items that are the most impactful for the variety classification. We find that the extracted lexical features are indeed representative of their respective varieties and note that the trained models also rely on place names for classifications.
The task of toxicity detection is still a relevant task, especially in the context of safe and fair LMs development. Nevertheless, labeled binary toxicity classification corpora are not available for all languages, which is understandable given the resource-intensive nature of the annotation process. Ukrainian, in particular, is among the languages lacking such resources. To our knowledge, there has been no existing toxicity classification corpus in Ukrainian. In this study, we aim to fill this gap by investigating cross-lingual knowledge transfer techniques and creating labeled corpora by: (i)~translating from an English corpus, (ii)~filtering toxic samples using keywords, and (iii)~annotating with crowdsourcing. We compare LLMs prompting and other cross-lingual transfer approaches with and without fine-tuning offering insights into the most robust and efficient baselines.