A global gathering for knowledge sharing, community building, and opportunities to define a roadmap of research and intervention priorities to improve science.

YouTube video by Democracy Now!

This link will take you to a page that’s not on LinkedIn

We Are There Now

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual lear...

YouTube video by Scientists for EU

Low isotropy in an embedding space impairs performance on tasks involving semantic inference. Our study investigates the impact of isotropy on semantic code search performance and explores post-proces...

Companion website to a long-running survey on text classification. - ascherp/text-classification-survey

Capitulation is contagious.

Continual learning remains challenging across various natural language understanding tasks. When models are updated with new training data, they risk catastrophic forgetting of prior knowledge. In the...

Message Passing Neural Networks (MPNNs) have demonstrated remarkable success in node classification on homophilic graphs. It has been shown that they do not solely rely on homophily but on...

Assigning a subset of labels from a fixed pool of labels to a given input text is a text classification problem with many real-world applications, such as in recommender systems. Two separate research...

Assessing the importance of individual training samples is a key challenge in machine learning. Traditional approaches retrain models with and without specific samples, which is computationally expens...

YouTube video by PBS NewsHour