Deep Learning

This paper introduces TaylorShift, a novel reformulation of the attention mechanism using Taylor softmax that enables computing full token-to-token interactions in linear time. We analytically and empirically determine the crossover points where employing TaylorShift becomes more efficient than traditional attention. TaylorShift outperforms the traditional transformer architecture in 4 out of 5 tasks.

A comprehensive benchmark and analysis of more than 45 transformer models for image classification to evaluate their efficiency, considering various performance metrics. We find the optimal architectures to use and uncover that model-scaling is more efficient than image scaling.

At its core, Albatross is a research project in the area of continual learning.

SustainML is dedicated to creating a sustainable ML framework for Green AI. By prioritizing energy efficiency, SustainML aims to pave the way for environmentally conscious AI solutions that are both efficient and effective.

We extend and test KEdge, an interpretable-by-design approach for graph neural networks, and compare it to gradient-based attribution techniques.