Related papers: No One Left Behind: How to Exploit the Incomplete …
Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenarios without…
Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks.…
Conversion rate (CVR) prediction is one of the most critical tasks for digital display advertising. Commercial systems often require to update models in an online learning manner to catch up with the evolving data distribution. However,…
Target localization is a critical task in sensitive applications, where multiple sensing agents communicate and collaborate to identify the target location based on sensor readings. Existing approaches investigated the use of Multi-Agent…
We describe a method and new no-code software tools enabling domain experts to build custom structured, labeled datasets from the unstructured text of documents and build niche machine learning text classification models traceable to…
Predicting the expected value or number of post-click conversions (purchases or other events) is a key task in performance-based digital advertising. In training a conversion optimizer model, one of the most crucial aspects is handling…
Multi-task learning (MTL) aims to empower a model to tackle multiple tasks simultaneously. A recent development known as task arithmetic has revealed that several models, each fine-tuned for distinct tasks, can be directly merged into a…
Click-Through Rate (CTR) prediction is essential in online advertising, where semantic information plays a pivotal role in shaping user decisions and enhancing CTR effectiveness. Capturing and modeling deep semantic information, such as a…
Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain,…
Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Recent approaches, such as XR-Transformer and LightXML, leverage a…
Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels…
Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…
Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency.…
Medical image segmentation is a fundamental yet challenging task due to the arduous process of acquiring large volumes of high-quality labeled data from experts. Contrastive learning offers a promising but still problematic solution to this…
Large language models (LLMs) are reshaping automated fact-checking (AFC) by enabling unified, end-to-end verification pipelines rather than isolated components. While large proprietary models achieve strong performance, their closed…
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in…
\textit{Complementary label learning} (CLL) requires annotators to give \emph{irrelevant} labels instead of relevant labels for instances. Currently, CLL has shown its promising performance on multi-class data by estimating a transition…
Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance. Typical MTL methods are jointly trained with the complete multitude of ground-truths for all tasks…
Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only…
One of the challenges in display advertising is that the distribution of features and click through rate (CTR) can exhibit large shifts over time due to seasonality, changes to ad campaigns and other factors. The predominant strategy to…