Revisiting Kernel Attention with Correlated Gaussian Process Representation

• URL: http://arxiv.org/abs/2502.20525v1
• Date: Thu, 27 Feb 2025 21:21:48 GMT
• Title: Revisiting Kernel Attention with Correlated Gaussian Process Representation
• Authors: Long Minh Bui, Tho Tran Huu, Duy Dinh, Tan Minh Nguyen, Trong Nghia Hoang,
• Abstract summary: We propose a new class of transformers whose self-attention units are modeled as cross-covariance between two correlated GPs (CGPs)<n>This allows asymmetries in attention and can enhance the representation capacity of GP-based transformers.<n>Our empirical studies show that both CGP-based and sparse CGP-based transformers achieve better performance than state-of-the-art GP-based transformers.
• Score: 6.857174439487293
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformers have increasingly become the de facto method to model sequential data with state-of-the-art performance. Due to its widespread use, being able to estimate and calibrate its modeling uncertainty is important to understand and design robust transformer models. To achieve this, previous works have used Gaussian processes (GPs) to perform uncertainty calibration for the attention units of transformers and attained notable successes. However, such approaches have to confine the transformers to the space of symmetric attention to ensure the necessary symmetric requirement of their GP's kernel specification, which reduces the representation capacity of the model. To mitigate this restriction, we propose the Correlated Gaussian Process Transformer (CGPT), a new class of transformers whose self-attention units are modeled as cross-covariance between two correlated GPs (CGPs). This allows asymmetries in attention and can enhance the representation capacity of GP-based transformers. We also derive a sparse approximation for CGP to make it scale better. Our empirical studies show that both CGP-based and sparse CGP-based transformers achieve better performance than state-of-the-art GP-based transformers on a variety of benchmark tasks. The code for our experiments is available at https://github.com/MinhLong210/CGP-Transformers.

Related papers

• Exploring the Integration of Key-Value Attention Into Pure and Hybrid Transformers for Semantic Segmentation [0.0]
  KV Transformer shows promising results in synthetic, NLP, and image classification tasks. This is especially conducive to use cases where local inference is required, such as medical screening applications.
  arXiv  Detail & Related papers  (2025-03-24T16:38:31Z)
• Converting Transformers into DGNNs Form [7.441691512676916]
  We introduce a synthetic unitary digraph convolution based on the digraph Fourier transform.<n>The resulting model, which we term Converter, effectively converts a Transformer into a Directed Graph Neural Network form.<n>We have tested Converter on Long-Range Arena benchmark, long document classification, and DNA sequence-based taxonomy classification.
  arXiv  Detail & Related papers  (2025-02-01T22:44:46Z)
• On the Convergence of Encoder-only Shallow Transformers [62.639819460956176]
  We build the global convergence theory of encoder-only shallow Transformers under a realistic setting. Our results can pave the way for a better understanding of modern Transformers, particularly on training dynamics.
  arXiv  Detail & Related papers  (2023-11-02T20:03:05Z)
• Deep Transformed Gaussian Processes [0.0]
  Transformed Gaussian Processes (TGPs) are processes specified by transforming samples from the joint distribution from a prior process (typically a GP) using an invertible transformation. We propose a generalization of TGPs named Deep Transformed Gaussian Processes (DTGPs), which follows the trend of concatenating layers of processes. Experiments conducted evaluate the proposed DTGPs in multiple regression datasets, achieving good scalability and performance.
  arXiv  Detail & Related papers  (2023-10-27T16:09:39Z)
• Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
  We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches. This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
  arXiv  Detail & Related papers  (2023-05-26T00:43:02Z)
• Calibrating Transformers via Sparse Gaussian Processes [23.218648177475135]
  We propose Sparse Gaussian Process attention (SGPA), which performs Bayesian inference directly in the output space of multi-head attention blocks (MHAs) in transformer to calibrate its uncertainty. On a suite of prediction tasks on text, images and graphs, SGPA-based Transformers achieve competitive predictive accuracy, while noticeably improving both in-distribution calibration and out-of-distribution robustness and detection.
  arXiv  Detail & Related papers  (2023-03-04T16:04:17Z)
• Full Stack Optimization of Transformer Inference: a Survey [58.55475772110702]
  Transformer models achieve superior accuracy across a wide range of applications. The amount of compute and bandwidth required for inference of recent Transformer models is growing at a significant rate. There has been an increased focus on making Transformer models more efficient.
  arXiv  Detail & Related papers  (2023-02-27T18:18:13Z)
• Your Transformer May Not be as Powerful as You Expect [88.11364619182773]
  We mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. We present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. We develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions.
  arXiv  Detail & Related papers  (2022-05-26T14:51:30Z)
• Gophormer: Ego-Graph Transformer for Node Classification [27.491500255498845]
  In this paper, we propose a novel Gophormer model which applies transformers on ego-graphs instead of full-graphs. Specifically, Node2Seq module is proposed to sample ego-graphs as the input of transformers, which alleviates the challenge of scalability. In order to handle the uncertainty introduced by the ego-graph sampling, we propose a consistency regularization and a multi-sample inference strategy.
  arXiv  Detail & Related papers  (2021-10-25T16:43:32Z)
• Visual Saliency Transformer [127.33678448761599]
  We develop a novel unified model based on a pure transformer, Visual Saliency Transformer (VST), for both RGB and RGB-D salient object detection (SOD) It takes image patches as inputs and leverages the transformer to propagate global contexts among image patches. Experimental results show that our model outperforms existing state-of-the-art results on both RGB and RGB-D SOD benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-25T08:24:06Z)
• Applying the Transformer to Character-level Transduction [68.91664610425114]
  The transformer has been shown to outperform recurrent neural network-based sequence-to-sequence models in various word-level NLP tasks. We show that with a large enough batch size, the transformer does indeed outperform recurrent models for character-level tasks.
  arXiv  Detail & Related papers  (2020-05-20T17:25:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.