Related papers: p-Laplacian Transformer
The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…
Recent developments in deep learning have revolutionized the paradigm of image restoration. However, its applications on real image denoising are still limited, due to its sensitivity to training data and the complex nature of real image…
We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). We begin by observing that Transformers generalize DeepSets, or first-order (set-input) permutation invariant MLPs. Then,…
Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…
In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained limited due to the difficulty of properly defining positions.…
Transformers are emerging as the new workhorse of NLP, showing great success across tasks. Unlike LSTMs, transformers process input sequences entirely through self-attention. Previous work has suggested that the computational capabilities…
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic…
Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in…
It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-trained Transformers (particularly for vision) to attempt to…
Learning to rank is an important task that has been successfully deployed in many real-world information retrieval systems. Most existing methods compute relevance judgments of documents independently, without holistically considering the…
In this work we consider a generalized bilevel optimization framework for solving inverse problems. We introduce fractional Laplacian as a regularizer to improve the reconstruction quality, and compare it with the total variation…
This paper is concerned with the numerical solution of a class of variational inequalities of the second kind, involving the $p$-Laplacian operator. This kind of problems arise, for instance, in the mathematical modelling of non-Newtonian…
Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in capturing token distances because the position or distance…
With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…
Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…
Transformers have emerged as a preferred model for many tasks in natural langugage processing and vision. Recent efforts on training and deploying Transformers more efficiently have identified many strategies to approximate the…
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing…
Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…
Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…
The graph Laplacian plays key roles in information processing of relational data, and has analogies with the Laplacian in differential geometry. In this paper, we generalize the analogy between graph Laplacian and differential geometry to…