Disentangling and Integrating Relational and Sensory Information in Transformer Architectures

• URL: http://arxiv.org/abs/2405.16727v1
• Date: Sun, 26 May 2024 23:52:51 GMT
• Title: Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
• Authors: Awni Altabaa, John Lafferty,
• Abstract summary: Transformer architecture processes sequences by implementing a form of neural message-passing. Two types of information are essential under this general computational paradigm. Standard attention naturally encodes the former, but does not explicitly encode the latter.
• Score: 2.5322020135765464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Transformer architecture processes sequences by implementing a form of neural message-passing that consists of iterative information retrieval (attention), followed by local processing (position-wise MLP). Two types of information are essential under this general computational paradigm: "sensory" information about individual objects, and "relational" information describing the relationships between objects. Standard attention naturally encodes the former, but does not explicitly encode the latter. In this paper, we present an extension of Transformers where multi-head attention is augmented with two distinct types of attention heads, each routing information of a different type. The first type is the standard attention mechanism of Transformers, which captures object-level features, while the second type is a novel attention mechanism we propose to explicitly capture relational information. The two types of attention heads each possess different inductive biases, giving the resulting architecture greater efficiency and versatility. The promise of this approach is demonstrated empirically across a range of tasks.

Related papers

• Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling [10.246977481606427]
  We study the mechanisms through which different components of Transformer, such as the dot-product self-attention, affect its expressive power. Our study reveals the roles of critical parameters in the Transformer, such as the number of layers and the number of attention heads.
  arXiv  Detail & Related papers  (2024-02-01T11:43:13Z)
• 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)
• Neural-Logic Human-Object Interaction Detection [67.4993347702353]
  We present L OGIC HOI, a new HOI detector that leverages neural-logic reasoning and Transformer to infer feasible interactions between entities. Specifically, we modify the self-attention mechanism in vanilla Transformer, enabling it to reason over the human, action, object> triplet and constitute novel interactions. We formulate these two properties in first-order logic and ground them into continuous space to constrain the learning process of our approach, leading to improved performance and zero-shot generalization capabilities.
  arXiv  Detail & Related papers  (2023-11-16T11:47:53Z)
• Solving Reasoning Tasks with a Slot Transformer [7.966351917016229]
  We present the Slot Transformer, an architecture that leverages slot attention, transformers and iterative variational inference on video scene data to infer representations. We evaluate the effectiveness of key components of the architecture, the model's representational capacity and its ability to predict from incomplete input.
  arXiv  Detail & Related papers  (2022-10-20T16:40:30Z)
• SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization [59.732036564862796]
  We propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object structure information into transformer for enhancing discriminative representation learning. The proposed two modules are light-weighted and can be plugged into any transformer network and trained end-to-end easily. Experiments and analyses demonstrate that the proposed SIM-Trans achieves state-of-the-art performance on fine-grained visual categorization benchmarks.
  arXiv  Detail & Related papers  (2022-08-31T03:00:07Z)
• Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence [17.854940064699985]
  We propose a transformer architecture with a mitigatory self-attention mechanism. Miti-DETR reserves the inputs of each single attention layer to the outputs of that layer so that the "non-attention" information has participated in attention propagation. Miti-DETR significantly enhances the average detection precision and convergence speed towards existing DETR-based models.
  arXiv  Detail & Related papers  (2021-12-26T03:23:59Z)
• Discrete-Valued Neural Communication [85.3675647398994]
  We show that restricting the transmitted information among components to discrete representations is a beneficial bottleneck. Even though individuals have different understandings of what a "cat" is based on their specific experiences, the shared discrete token makes it possible for communication among individuals to be unimpeded by individual differences in internal representation. We extend the quantization mechanism from the Vector-Quantized Variational Autoencoder to multi-headed discretization with shared codebooks and use it for discrete-valued neural communication.
  arXiv  Detail & Related papers  (2021-07-06T03:09:25Z)
• Transformers with Competitive Ensembles of Independent Mechanisms [97.93090139318294]
  We propose a new Transformer layer which divides the hidden representation and parameters into multiple mechanisms, which only exchange information through attention. We study TIM on a large-scale BERT model, on the Image Transformer, and on speech enhancement and find evidence for semantically meaningful specialization as well as improved performance.
  arXiv  Detail & Related papers  (2021-02-27T21:48:46Z)
• 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)
• Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction [64.03526633651218]
  Click-Through Rate (CTR) prediction is one of the most important machine learning tasks in recommender systems. We propose an automated interaction architecture discovering framework for CTR prediction named AutoCTR.
  arXiv  Detail & Related papers  (2020-06-29T04:33:01Z)

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.