Related papers: OpenIE6: Iterative Grid Labeling and Coordination …

Reasoning over structured graphs remains a fundamental challenge for Large Language Models (LLMs), particularly when scaling to large graphs. Existing approaches typically follow the retrieval-augmented generation (RAG) paradigm: first…

Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship between labels in the past task and the new task with or…

This work studies ensemble learning for graph neural networks (GNNs) under the popular semi-supervised setting. Ensemble learning has shown superiority in improving the accuracy and robustness of traditional machine learning by combining…

We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these techniques for supervised learning, we establish a connection between…

Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner. Thus…

Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address…

LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yields limited gains. To address this, we propose ProUIE, a…

Active learning selects the most informative samples to exploit limited annotation budgets. Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times. In this paper,…

Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts. Evaluation of the approaches,…

Knowledge graphs, a powerful tool for structuring information through relational triplets, have recently become the new front-runner in enhancing question-answering systems. While traditional Retrieval Augmented Generation (RAG) approaches…

The work presented in this master thesis consists of extracting a set of events from texts written in natural language. For this purpose, we have based ourselves on the basic notions of the information extraction as well as the open…

Time-series anomaly detection is an important task and has been widely applied in the industry. Since manual data annotation is expensive and inefficient, most applications adopt unsupervised anomaly detection methods, but the results are…

Federated Learning (FL) has emerged as a promising solution to perform deep learning on different data owners without exchanging raw data. However, non-IID data has been a key challenge in FL, which could significantly degrade the accuracy…

We propose Tree Variational Autoencoder (TreeVAE), a new generative hierarchical clustering model that learns a flexible tree-based posterior distribution over latent variables. TreeVAE hierarchically divides samples according to their…

Non-IID dataset and heterogeneous environment of the local clients are regarded as a major issue in Federated Learning (FL), causing a downturn in the convergence without achieving satisfactory performance. In this paper, we propose a novel…

The development of deep learning based image representation learning (IRL) methods has attracted great attention for various image understanding problems. Most of these methods require the availability of a high quantity and quality of…

Federated learning (FL) has recently emerged as a promising technology to enable artificial intelligence (AI) at the network edge, where distributed mobile devices collaboratively train a shared AI model under the coordination of an edge…

Transparent and standardized documentation is essential for building trustworthy generative AI (GAI) systems. However, existing automated methods for generating model and data cards still face three major challenges: (i) static templates,…

Although Hierarchical Federated Learning (HFL) utilizes edge servers (ESs) to alleviate communication burdens, its model performance will be degraded by non-IID data and limited communication resources. Current works often assume that data…

Information Extraction (IE) systems are traditionally domain-specific, requiring costly adaptation that involves expert schema design, data annotation, and model training. While Large Language Models have shown promise in zero-shot IE,…