Related papers: Attention Meets Post-hoc Interpretability: A Mathe…

Encoder-decoder networks with attention have proven to be a powerful way to solve many sequence-to-sequence tasks. In these networks, attention aligns encoder and decoder states and is often used for visualizing network behavior. However,…

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the…

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug…

Leveraging data collected from smart meters in buildings can aid in developing policies towards energy conservation. Significant energy savings could be realised if deviations in the building operating conditions are detected early, and…

Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In…

Benefiting from the capability of building inter-dependencies among channels or spatial locations, attention mechanisms have been extensively studied and broadly used in a variety of computer vision tasks recently. In this paper, we…

Attention mechanisms have become integral in AI, significantly enhancing model performance and scalability by drawing inspiration from human cognition. Concurrently, the Attention Schema Theory (AST) in cognitive science posits that…

Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the…

Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention architecture matters more than parameter count. Studying three circuit types across Pythia…

This paper targets two transformer attention based interpretability methods working with local abstraction and global representation, in the context of time series data. We distinguish local and global contexts, and provide a comprehensive…

Transformers, and the attention mechanism in particular, have become ubiquitous in machine learning. Their success in modeling nonlocal, long-range correlations has led to their widespread adoption in natural language processing, computer…

In this work, we present the first general logic of attention. Attention is a powerful cognitive ability that allows agents to focus on potentially complex information, such as logically structured propositions, higher-order beliefs, or…

Large language models are able to exploit in-context learning to access external knowledge beyond their training data through retrieval-augmentation. While promising, its inner workings remain unclear. In this work, we shed light on the…

In humans, Attention is a core property of all perceptual and cognitive operations. Given our limited ability to process competing sources, attention mechanisms select, modulate, and focus on the information most relevant to behavior. For…

Explainable Recommendation has attracted a lot of attention due to a renewed interest in explainable artificial intelligence. In particular, post-hoc approaches have proved to be the most easily applicable ones to increasingly complex…

I study how past and future choices are linked in the framework of attention. Attention cannot be observed but past choices are necessarily considered in future decisions. This link connects two types of rationality violations,…

We introduced a {\it working memory} augmented adaptive controller in our recent work. The controller uses attention to read from and write to the working memory. Attention allows the controller to read specific information that is relevant…

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Growing evidence suggests that the brain uses an attention schema, or a simplified model of attention, to help control what it attends to. One proposed benefit of this model is to allow agents to model the attention states of other agents,…