An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models

• URL: http://arxiv.org/abs/2212.14852v3
• Date: Mon, 1 Apr 2024 03:51:06 GMT
• Title: An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models
• Authors: Yufeng Zhang, Boyi Liu, Qi Cai, Lingxiao Wang, Zhaoran Wang,
• Abstract summary: We show that input tokens are often exchangeable since they already include positional encodings. We establish the existence of a sufficient and minimal representation of input tokens. We prove that attention with the desired parameter infers the latent posterior up to an approximation error.
• Score: 64.87562101662952
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a rigorous theory on how the attention mechanism achieves it. In particular, several intriguing questions remain open: (a) What makes a desirable representation? (b) How does the attention mechanism infer the desirable representation within the forward pass? (c) How does a pretraining procedure learn to infer the desirable representation through the backward pass? We observe that, as is the case in BERT and ViT, input tokens are often exchangeable since they already include positional encodings. The notion of exchangeability induces a latent variable model that is invariant to input sizes, which enables our theoretical analysis. - To answer (a) on representation, we establish the existence of a sufficient and minimal representation of input tokens. In particular, such a representation instantiates the posterior distribution of the latent variable given input tokens, which plays a central role in predicting output labels and solving downstream tasks. - To answer (b) on inference, we prove that attention with the desired parameter infers the latent posterior up to an approximation error, which is decreasing in input sizes. In detail, we quantify how attention approximates the conditional mean of the value given the key, which characterizes how it performs relational inference over long sequences. - To answer (c) on learning, we prove that both supervised and self-supervised objectives allow empirical risk minimization to learn the desired parameter up to a generalization error, which is independent of input sizes. Particularly, in the self-supervised setting, we identify a condition number that is pivotal to solving downstream tasks.

Related papers

• Identifiable Representation and Model Learning for Latent Dynamic Systems [0.0]
  We study the problem of identifiable representation and model learning for latent dynamic systems. We prove that, for linear or affine nonlinear latent dynamic systems, it is possible to identify the representations up to scaling and determine the models up to some simple transformations.
  arXiv  Detail & Related papers  (2024-10-23T13:55:42Z)
• Are queries and keys always relevant? A case study on Transformer wave functions [0.0]
  dot product attention mechanism, originally designed for natural language processing (NLP) tasks, is a cornerstone of modern Transformers. We explore the suitability of Transformers, focusing on their attention mechanisms, in the specific domain of the parametrization of variational wave functions.
  arXiv  Detail & Related papers  (2024-05-29T08:32:37Z)
• A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks [29.764014766305174]
  We show how a transformer model is able to perform ICL under reasonable assumptions on the pre-training process and the downstream tasks. We establish that this entire procedure is implementable using the transformer mechanism.
  arXiv  Detail & Related papers  (2023-05-26T15:49:43Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• Causally-motivated Shortcut Removal Using Auxiliary Labels [63.686580185674195]
  Key challenge to learning such risk-invariant predictors is shortcut learning. We propose a flexible, causally-motivated approach to address this challenge. We show both theoretically and empirically that this causally-motivated regularization scheme yields robust predictors.
  arXiv  Detail & Related papers  (2021-05-13T16:58:45Z)
• Attention that does not Explain Away [54.42960937271612]
  Models based on the Transformer architecture have achieved better accuracy than the ones based on competing architectures for a large set of tasks. A unique feature of the Transformer is its universal application of a self-attention mechanism, which allows for free information flow at arbitrary distances. We propose a doubly-normalized attention scheme that is simple to implement and provides theoretical guarantees for avoiding the "explaining away" effect.
  arXiv  Detail & Related papers  (2020-09-29T21:05:39Z)
• Tractable Inference in Credal Sentential Decision Diagrams [116.6516175350871]
  Probabilistic sentential decision diagrams are logic circuits where the inputs of disjunctive gates are annotated by probability values. We develop the credal sentential decision diagrams, a generalisation of their probabilistic counterpart that allows for replacing the local probabilities with credal sets of mass functions. For a first empirical validation, we consider a simple application based on noisy seven-segment display images.
  arXiv  Detail & Related papers  (2020-08-19T16:04:34Z)
• Learning Disentangled Representations with Latent Variation Predictability [102.4163768995288]
  This paper defines the variation predictability of latent disentangled representations. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
  arXiv  Detail & Related papers  (2020-07-25T08:54:26Z)
• Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers [42.93754828584075]
  We present a new Transformer architecture, Performer, based on Fast Attention Via Orthogonal Random features (FAVOR) Our mechanism scales linearly rather than quadratically in the number of tokens in the sequence, is characterized by sub-quadratic space complexity and does not incorporate any sparsity pattern priors. It provides strong theoretical guarantees: unbiased estimation of the attention matrix and uniform convergence.
  arXiv  Detail & Related papers  (2020-06-05T17:09:16Z)

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.