Titlebook: Machine Learning and Knowledge Discovery in Databases. Research Track; European Conference, Albert Bifet,Jesse Davis,Indrė Žliobaitė Confer

CANDY

Low-Hanging Fruit: Knowledge Distillation from Noisy Teachers for Open Domain Spoken Language Underss, which are impractical for open-domain SLU, given the wide variety of topics that must be considered. As the dataset grows exponentially, significant costs are inevitably incurred in achieving open-domain SLU. The Noisy Teacher and Consistently Guiding Student (NTCG) Paradigm is proposed to addres

IRK

The Price of Labelling: A Two-Phase Federated Self-learning Approachting studies on FL primarily focus on supervised learning, assuming that all clients possess sufficient training data with ground-truth labels, this assumption may not always hold in practical scenarios. In many cases, data are unlabelled due to labeling costs, time constraints, or lack of expertise

conduct

Disentangled Representations for Continual Learning: Overcoming Forgetting and Facilitating Knowledgmake full use of the knowledge from multiple tasks to solve a particular task. In this paper, we propose to disentangle representations in continual learning into task-shared and task-specific representations, using shared and task-specific encoders to obtain the corresponding disentangled represent

上釉彩

叫喊

PACK

Novel Node Category Detection Under Subpopulation Shifttions of existing categories. It is often important to detect nodes of novel categories under such distribution shifts for safety or insight discovery purposes. We introduce a new approach, Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP), to detect nodes belonging to novel

Incisor

SynODC: Utilizing the Syntactic Structure for Outlier Detection in Categorical Attributesained on a low quality data tend to produce inaccurate decisions and poor predictions. While detecting outliers in numerical data has been extensively studied, few attempts were made to solve the problem of detecting outliers in attributes with categorical values. In this paper, we introduce SynODC

Cultivate

FELIX: Automatic and Interpretable Feature Engineering Using LLMsuracy against interpretability, all while having to deal with unstructured data. We address this issue by introducing. . . . . . . . . . (FELIX), a novel approach harnessing the vast world knowledge embedded in pre-trained Large Language Models (LLMs) to automatically generate a set of features desc

N斯巴达人

Harnessing Superclasses for Learning from Hierarchical Databaseslasses in superclasses. We introduce a loss for this type of supervised hierarchical classification. It utilizes the knowledge of the hierarchy to assign each example not only to a class but also to all encompassing superclasses. Applicable to any feedforward architecture with a softmax output layer

显微镜

Approximation Error of Sobolev Regular Functions with Tanh Neural Networks: Theoretical Impact on PI theoretical guarantees in Sobolev norm. In this paper, we conduct an extensive functional analysis, unveiling tighter approximation bounds compared to prior works, especially for higher order PDEs. These better guarantees translate into smaller PINN architectures and improved generalization error w