Related papers: Learning Slice-Aware Representations with Mixture …

Multiple instance learning (MIL) is often used in medical imaging to classify high-resolution 2D images by processing patches or classify 3D volumes by processing slices. However, conventional MIL approaches treat instances separately,…

The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the demand for understanding complex relationships grows,…

Adaptive causal representation learning from observational data is presented, integrated with an efficient sample splitting technique within the semiparametric estimating equation framework. The support points sample splitting (SPSS), a…

Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound.…

Attention, or prioritization of certain information items over others, is a critical element of any learning process, for both humans and machines. Given that humans continue to outperform machines in certain learning tasks, it seems…

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

As one of the most popular neural network modules, Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing. The effectiveness of the…

Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large…

Large Language Models (LLMs) often exhibit systematic errors on specific subsets of data, known as error slices. For instance, a slice can correspond to a certain demographic, where a model does poorly in identifying toxic comments…

Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention heads can be pruned without significant…

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused…

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…

In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we propose Multi-head Explicit Attention (MEA), a simple yet…

Human perception of the empirical world involves recognizing the diverse appearances, or 'modalities', of underlying objects. Despite the longstanding consideration of this perspective in philosophy and cognitive science, the study of…

The Multiple Instance Learning (MIL) paradigm is attracting plenty of attention in medical imaging classification, where labeled data is scarce. MIL methods cast medical images as bags of instances (e.g. patches in whole slide images, or…

The application of computer vision is gradually increasing across various domains. They employ deep learning models with a black-box nature. Without the ability to explain the behavior of neural networks, especially their decision-making…

Standard softmax self-attention excels in vision tasks but incurs quadratic complexity O(N^2), limiting high-resolution deployment. Linear attention reduces the cost to O(N), yet its compressed state representations can impair modeling…

The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality but suffers from large Key-Value (KV) cache memory…