Are queries and keys always relevant? A case study on Transformer wave functions

• URL: http://arxiv.org/abs/2405.18874v1
• Date: Wed, 29 May 2024 08:32:37 GMT
• Title: Are queries and keys always relevant? A case study on Transformer wave functions
• Authors: Riccardo Rende, Luciano Loris Viteritti,
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The dot product attention mechanism, originally designed for natural language processing (NLP) tasks, is a cornerstone of modern Transformers. It adeptly captures semantic relationships between word pairs in sentences by computing a similarity overlap between queries and keys. In this work, we explore the suitability of Transformers, focusing on their attention mechanisms, in the specific domain of the parametrization of variational wave functions to approximate ground states of quantum many-body spin Hamiltonians. Specifically, we perform numerical simulations on the two-dimensional $J_1$-$J_2$ Heisenberg model, a common benchmark in the field of quantum-many body systems on lattice. By comparing the performance of standard attention mechanisms with a simplified version that excludes queries and keys, relying solely on positions, we achieve competitive results while reducing computational cost and parameter usage. Furthermore, through the analysis of the attention maps generated by standard attention mechanisms, we show that the attention weights become effectively input-independent at the end of the optimization. We support the numerical results with analytical calculations, providing physical insights of why queries and keys should be, in principle, omitted from the attention mechanism when studying large systems. Interestingly, the same arguments can be extended to the NLP domain, in the limit of long input sentences.

Related papers

• DAPE V2: Process Attention Score as Feature Map for Length Extrapolation [63.87956583202729]
  We conceptualize attention as a feature map and apply the convolution operator to mimic the processing methods in computer vision. The novel insight, which can be adapted to various attention-related models, reveals that the current Transformer architecture has the potential for further evolution.
  arXiv  Detail & Related papers  (2024-10-07T07:21:49Z)
• Correlated Attention in Transformers for Multivariate Time Series [22.542109523780333]
  We propose a novel correlated attention mechanism, which efficiently captures feature-wise dependencies, and can be seamlessly integrated within the encoder blocks of existing Transformers. In particular, correlated attention operates across feature channels to compute cross-covariance matrices between queries and keys with different lag values, and selectively aggregate representations at the sub-series level. This architecture facilitates automated discovery and representation learning of not only instantaneous but also lagged cross-correlations, while inherently capturing time series auto-correlation.
  arXiv  Detail & Related papers  (2023-11-20T17:35:44Z)
• Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning [5.41530201129053]
  This paper proposes a novel memorization-based inference (MBI) that is compute free and only requires lookups. Specifically, our work capitalizes on the inference mechanism of the recurrent attention model (RAM) By leveraging the low-dimensionality of glimpse, our inference procedure stores key value pairs comprising of glimpse location, patch vector, etc. in a table. The computations are obviated during inference by utilizing the table to read out key-value pairs and performing compute-free inference by memorization.
  arXiv  Detail & Related papers  (2023-07-14T21:01:59Z)
• An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models [64.87562101662952]
  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.
  arXiv  Detail & Related papers  (2022-12-30T17:59:01Z)
• How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers [59.57128476584361]
  We introduce PAPA, a new probing method that replaces the input-dependent attention matrices with constant ones. We find that without any input-dependent attention, all models achieve competitive performance. We show that better-performing models lose more from applying our method than weaker models, suggesting that the utilization of the input-dependent attention mechanism might be a factor in their success.
  arXiv  Detail & Related papers  (2022-11-07T12:37:54Z)
• Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers [50.85524803885483]
  This work proposes a formal definition of statistically meaningful (SM) approximation which requires the approximating network to exhibit good statistical learnability. We study SM approximation for two function classes: circuits and Turing machines.
  arXiv  Detail & Related papers  (2021-07-28T04:28:55Z)
• Accurate methods for the analysis of strong-drive effects in parametric gates [94.70553167084388]
  We show how to efficiently extract gate parameters using exact numerics and a perturbative analytical approach. We identify optimal regimes of operation for different types of gates including $i$SWAP, controlled-Z, and CNOT.
  arXiv  Detail & Related papers  (2021-07-06T02:02:54Z)
• Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation [58.80806716024701]
  We study the global structure of attention scores computed using dot-product based self-attention. We find that most of the variation among attention scores lie in a low-dimensional eigenspace. We propose to compute scores only for a partial subset of token pairs, and use them to estimate scores for the remaining pairs.
  arXiv  Detail & Related papers  (2021-06-16T14:38:42Z)
• Adding machine learning within Hamiltonians: Renormalization group transformations, symmetry breaking and restoration [0.0]
  We include the predictive function of a neural network, designed for phase classification, as a conjugate variable coupled to an external field within the Hamiltonian of a system. Results show that the field can induce an order-disorder phase transition by breaking or restoring the symmetry. We conclude by discussing how the method provides an essential step toward bridging machine learning and physics.
  arXiv  Detail & Related papers  (2020-09-30T18:44:18Z)

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.