Related papers: Dataset Cartography: Mapping and Diagnosing Datase…

With increasing applications of semantic segmentation, numerous datasets have been proposed in the past few years. Yet labeling remains expensive, thus, it is desirable to jointly train models across aggregations of datasets to enhance data…

Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process for subjective natural language…

Differential equations are a ubiquitous tool to study dynamics, ranging from physical systems to complex systems, where a large number of agents interact through a graph with non-trivial topological features. Data-driven approximations of…

Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes…

This article addresses the challenge of adapting data-based models over time. We propose a novel two-fold modelling architecture designed to correct plant-model mismatch caused by two types of uncertainty. Out-of-domain uncertainty arises…

The practical success of much of NLP depends on the availability of training data. However, in real-world scenarios, training data is often scarce, not least because many application domains are restricted and specific. In this work, we…

Although learning from data is effective and has achieved significant milestones, it has many challenges and limitations. Learning from data starts from observations and then proceeds to broader generalizations. This framework is…

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models,…

Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in…

Distributed data mining (DDM) deals with the problem of finding patterns or models, called knowledge, in an environment with distributed data and computations. Today, a massive amounts of data which are often geographically distributed and…

Data quality is a key element for building and optimizing good learning models. Despite many attempts to characterize data quality, there is still a need for rigorous formalization and an efficient measure of the quality from available…

The labelling difficulty has been a longstanding problem in deep image matting. To escape from fine labels, this work explores using rough annotations such as trimaps coarsely indicating the foreground/background as supervision. We present…

To create state-of-the-art models for many downstream tasks, it has become common practice to fine-tune a pre-trained large vision model. However, it remains an open question of how to best determine which of the many possible model…

Deep Learning has thrived on the emergence of biomedical big data. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors such as operation policies, machine protocols,…

The essence of deep learning is to exploit data to train a deep neural network (DNN) model. This work explores the reverse process of generating data from a model, attempting to reveal the relationship between the data and the model. We…

Datasets of real-world applications are characterized by entities of different types, which are defined by multiple features and connected via varied types of relationships. A critical challenge for these datasets is developing models and…

Recent diagnostic datasets on compositional generalization, such as SCAN (Lake and Baroni, 2018) and COGS (Kim and Linzen, 2020), expose severe problems in models trained from scratch on these datasets. However, in contrast to this poor…

There has been significant research done on developing methods for improving robustness to distributional shift and uncertainty estimation. In contrast, only limited work has examined developing standard datasets and benchmarks for…

Data Science is a multidisciplinary field that plays a crucial role in extracting valuable insights and knowledge from large and intricate datasets. Within the realm of Data Science, two fundamental components are Information Theory (IT)…