Hierarchical Multi-Label Classification (HMC) faces critical challenges in maintaining structural consistency and balancing loss weighting in Multi-Task Learning (MTL). In order to address these issues, we propose a classifier called HCAL based on MTL integrated with prototype contrastive learning and adaptive task-weighting mechanisms. The most significant advantage of our classifier is semantic consistency including both prototype with explicitly modeling label and feature aggregation from child classes to parent classes. The other important advantage is an adaptive loss-weighting mechanism that dynamically allocates optimization resources by monitoring task-specific convergence rates. It effectively resolves the "one-strong-many-weak" optimization bias inherent in traditional MTL approaches. To further enhance robustness, a prototype perturbation mechanism is formulated by injecting controlled noise into prototype to expand decision boundaries. Additionally, we formalize a quantitative metric called Hierarchical Violation Rate (HVR) as to evaluate hierarchical consistency and generalization. Extensive experiments across three datasets demonstrate both the higher classification accuracy and reduced hierarchical violation rate of the proposed classifier over baseline models.

We address the task of hierarchical multi-label classification (HMC) of scientific documents at an industrial scale, where hundreds of thousands of documents must be classified across thousands of dynamic labels. The rapid growth of scientific publications necessitates scalable and efficient methods for classification, further complicated by the evolving nature of taxonomies--where new categories are introduced, existing ones are merged, and outdated ones are deprecated. Traditional machine learning approaches, which require costly retraining with each taxonomy update, become impractical due to the high overhead of labelled data collection and model adaptation. Large Language Models (LLMs) have demonstrated great potential in complex tasks such as multi-label classification. However, applying them to large and dynamic taxonomies presents unique challenges as the vast number of labels can exceed LLMs' input limits. In this paper, we present novel methods that combine the strengths of LLMs with dense retrieval techniques to overcome these challenges. Our approach avoids retraining by leveraging zero-shot HMC for real-time label assignment. We evaluate the effectiveness of our methods on SSRN, a large repository of preprints spanning multiple disciplines, and demonstrate significant improvements in both classification accuracy and cost-efficiency. By developing a tailored evaluation framework for dynamic taxonomies and publicly releasing our code, this research provides critical insights into applying LLMs for document classification, where the number of classes corresponds to the number of nodes in a large taxonomy, at an industrial scale.

In this work, we apply state-of-the-art self-supervised learning techniques on a large dataset of seafloor imagery, \textit{BenthicNet}, and study their performance for a complex hierarchical multi-label (HML) classification downstream task. In particular, we demonstrate the capacity to conduct HML training in scenarios where there exist multiple levels of missing annotation information, an important scenario for handling heterogeneous real-world data collected by multiple research groups with differing data collection protocols. We find that, when using smaller one-hot image label datasets typical of local or regional scale benthic science projects, models pre-trained with self-supervision on a larger collection of in-domain benthic data outperform models pre-trained on ImageNet. In the HML setting, we find the model can attain a deeper and more precise classification if it is pre-trained with self-supervision on in-domain data. We hope this work can establish a benchmark for future models in the field of automated underwater image annotation tasks and can guide work in other domains with hierarchical annotations of mixed resolution.

Our contributions are as follows: Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated We extend the EDR framework of [32] to address the HMC improved consistency and accuracy by enforcing constraints on problem without prior knowledge of the hierarchy by both a neural model during training. However, such work assumes the extending the language of that work and presenting a new existence of such constraints a-priori. In this paper, we relax this Focused-EDR which addresses an objective function mismatch strong assumption and present an approach based on Error Detection of [32] by leveraging approximate optimization of Rules (EDR) that allow for learning explainable rules about the ratio of two submodular functions; the failure modes of machine learning models. We show that these We demonstrate how our new approach, provides significant rules are not only effective in detecting when a machine learning improvement in the detection of errors when compared to a classifier has made an error but also can be leveraged as constraints black-box baseline neural error detector and the detection for HMC, thereby allowing the recovery of explainable constraints algorithm of [32] on three different HMC datasets; even if they are not provided. We show that our approach is effective We show our approach can recover constraints and that in detecting machine learning errors and recovering constraints, both the F1-score of constraints recovered as well as error is noise tolerant, and can function as a source of knowledge for F1 degrades gracefully with noise - with noise injected in a neurosymbolic models on multiple datasets, including a newly introduced manner to remove certain classes from consideration; military vehicle recognition dataset. We show the recovered constraints can then be used as a source for in neurosymbolic model learning (i.e., Logic Tensor Networks (LTN) [4]) to provide improved model performance

Memes are one of the most popular types of content used in an online disinformation campaign. They are primarily effective on social media platforms since they can easily reach many users. Memes in a disinformation campaign achieve their goal of influencing the users through several rhetorical and psychological techniques, such as causal oversimplification, name-calling, and smear. The SemEval 2024 Task 4 \textit{Multilingual Detection of Persuasion Technique in Memes} on identifying such techniques in the memes is divided across three sub-tasks: ($\mathbf{1}$) Hierarchical multi-label classification using only textual content of the meme, ($\mathbf{2}$) Hierarchical multi-label classification using both, textual and visual content of the meme and ($\mathbf{3}$) Binary classification of whether the meme contains a persuasion technique or not using it's textual and visual content. This paper proposes an ensemble of Class Definition Prediction (CDP) and hyperbolic embeddings-based approaches for this task. We enhance meme classification accuracy and comprehensiveness by integrating HypEmo's hierarchical label embeddings (Chen et al., 2023) and a multi-task learning framework for emotion prediction. We achieve a hierarchical F1-score of 0.60, 0.67, and 0.48 on the respective sub-tasks.

Vaccine concerns are an ever-evolving target, and can shift quickly as seen during the COVID-19 pandemic. Identifying longitudinal trends in vaccine concerns and misinformation might inform the healthcare space by helping public health efforts strategically allocate resources or information campaigns. We explore the task of detecting vaccine concerns in online discourse using large language models (LLMs) in a zero-shot setting without the need for expensive training datasets. Since real-time monitoring of online sources requires large-scale inference, we explore cost-accuracy trade-offs of different prompting strategies and offer concrete takeaways that may inform choices in system designs for current applications. An analysis of different prompting strategies reveals that classifying the concerns over multiple passes through the LLM, each consisting a boolean question whether the text mentions a vaccine concern or not, works the best. Our results indicate that GPT-4 can strongly outperform crowdworker accuracy when compared to ground truth annotations provided by experts on the recently introduced VaxConcerns dataset, achieving an overall F1 score of 78.7%.

Hierarchical multi-label text classification aims to classify the input text into multiple labels, among which the labels are structured and hierarchical. It is a vital task in many real world applications, e.g. scientific literature archiving. In this paper, we survey the recent progress of hierarchical multi-label text classification, including the open sourced data sets, the main methods, evaluation metrics, learning strategies and the current challenges. A few future research directions are also listed for community to further improve this field.

This work aims at hierarchical multi-label patents classification for patents disclosing technologies related to green plastics. This is an emerging field for which there is currently no classification scheme, and hence, no labeled data is available, making this task particularly challenging. We first propose a classification scheme for this technology and a way to learn a machine learning model to classify patents into the proposed classification scheme. To achieve this, we come up with a strategy to automatically assign labels to patents in order to create a labeled training dataset that can be used to learn a classification model in a supervised learning setting. Using said training dataset, we come up with two classification models, a SciBERT Neural Network (SBNN) model and a SciBERT Hierarchical Neural Network (SBHNN) model. Both models use a BERT model as a feature extractor and on top of it, a neural network as a classifier. We carry out extensive experiments and report commonly evaluation metrics for this challenging classification problem. The experiment results verify the validity of our approach and show that our model sets a very strong benchmark for this problem. We also interpret our models by visualizing the word importance given by the trained model, which indicates the model is capable to extract high-level semantic information of input documents. Finally, we highlight how our solution fulfills the evaluation criteria for the EPO CodeFest and we also outline possible directions for future work. Our code has been made available at https://github.com/epo/CF22-Green-Hands

Semi-supervised learning (SSL) is a common approach to learning predictive models using not only labeled examples, but also unlabeled examples. While SSL for the simple tasks of classification and regression has received a lot of attention from the research community, this is not properly investigated for complex prediction tasks with structurally dependent variables. This is the case of multi-label classification and hierarchical multi-label classification tasks, which may require additional information, possibly coming from the underlying distribution in the descriptive space provided by unlabeled examples, to better face the challenging task of predicting simultaneously multiple class labels. In this paper, we investigate this aspect and propose a (hierarchical) multi-label classification method based on semi-supervised learning of predictive clustering trees. We also extend the method towards ensemble learning and propose a method based on the random forest approach. Extensive experimental evaluation conducted on 23 datasets shows significant advantages of the proposed method and its extension with respect to their supervised counterparts. Moreover, the method preserves interpretability and reduces the time complexity of classical tree-based models.

The availability of genomic data has grown exponentially in the last decade, mainly due to the development of new sequencing technologies. Based on the interactions between genes (and gene products) extracted from the increasing genomic data, numerous studies have focused on the identification of associations between genes and functions. While these studies have shown great promise, the problem of annotating genes with functions remains an open challenge. In this work, we present a method to detect missing annotations in hierarchical multi-label classification datasets. We propose a method that exploits the class hierarchy by computing aggregated probabilities to the paths of classes from the leaves to the root for each instance. The proposed method is presented in the context of predicting missing gene function annotations, where these aggregated probabilities are further used to select a set of annotations to be verified through in vivo experiments. The experiments on Oriza sativa Japonica, a variety of rice, showcase that incorporating the hierarchy of classes into the method often improves the predictive performance and our proposed method yields superior results when compared to competitor methods from the literature. Genomic data has become exponentially available in the last decade, mainly due to the development of new technologies, including gene expression profiling generated with RNA sequencing (Ranganathan, Gribskov, Nakai and Schönbach, 2019). Based on the interactions between genes (and gene products) extracted from the increasing genomic data, numerous studies have focused on the identification of associations between genes and functions (Rust, Mongin and Birney, 2002; Vandepoele, Quimbaya, Casneuf, De Veylder and Van de Peer, 2009; van Dam, Võsa, van der Graaf, Franke and de Magalhães, 2017).