Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
- URL: http://arxiv.org/abs/2406.04090v2
- Date: Tue, 05 Nov 2024 20:51:06 GMT
- Title: Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
- Authors: Tam Thuc Do, Parham Eftekhar, Seyed Alireza Hosseini, Gene Cheung, Philip Chou,
- Abstract summary: We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms.
A normalized signal-dependent graph learning module amounts to a variant of the basic self-attention mechanism in conventional transformers.
- Score: 16.04850782310842
- License:
- Abstract: We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph total variation (GTV) -- subject to an interpolation constraint. The crucial insight is that a normalized signal-dependent graph learning module amounts to a variant of the basic self-attention mechanism in conventional transformers. Unlike "black-box" transformers that require learning of large key, query and value matrices to compute scaled dot products as affinities and subsequent output embeddings, resulting in huge parameter sets, our unrolled networks employ shallow CNNs to learn low-dimensional features per node to establish pairwise Mahalanobis distances and construct sparse similarity graphs. At each layer, given a learned graph, the target interpolated signal is simply a low-pass filtered output derived from the minimization of an assumed graph smoothness prior, leading to a dramatic reduction in parameter count. Experiments for two image interpolation applications verify the restoration performance, parameter efficiency and robustness to covariate shift of our graph-based unrolled networks compared to conventional transformers.
Related papers
- Variable-size Symmetry-based Graph Fourier Transforms for image compression [65.7352685872625]
We propose a new family of Symmetry-based Graph Fourier Transforms of variable sizes into a coding framework.
Our proposed algorithm generates symmetric graphs on the grid by adding specific symmetrical connections between nodes.
Experiments show that SBGFTs outperform the primary transforms integrated in the explicit Multiple Transform Selection.
arXiv Detail & Related papers (2024-11-24T13:00:44Z) - SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity [74.51827323742506]
We evaluate the necessity of adopting multi-layer attentions in Transformers on graphs.
We show that one-layer propagation can be reduced to one-layer propagation, with the same capability for representation learning.
It suggests a new technical path for building powerful and efficient Transformers on graphs.
arXiv Detail & Related papers (2024-09-13T17:37:34Z) - Graph as Point Set [31.448841287258116]
This paper introduces a novel graph-to-set conversion method that transforms interconnected nodes into a set of independent points.
It enables using set encoders to learn from graphs, thereby significantly expanding the design space of Graph Neural Networks.
To demonstrate the effectiveness of our approach, we introduce Point Set Transformer (PST), a transformer architecture that accepts a point set converted from a graph as input.
arXiv Detail & Related papers (2024-05-05T02:29:41Z) - Deep Prompt Tuning for Graph Transformers [55.2480439325792]
Fine-tuning is resource-intensive and requires storing multiple copies of large models.
We propose a novel approach called deep graph prompt tuning as an alternative to fine-tuning.
By freezing the pre-trained parameters and only updating the added tokens, our approach reduces the number of free parameters and eliminates the need for multiple model copies.
arXiv Detail & Related papers (2023-09-18T20:12:17Z) - Entropy Transformer Networks: A Learning Approach via Tangent Bundle
Data Manifold [8.893886200299228]
This paper focuses on an accurate and fast approach for image transformation employed in the design of CNN architectures.
A novel Entropy STN (ESTN) is proposed that interpolates on the data manifold distributions.
Experiments on challenging benchmarks show that the proposed ESTN can improve predictive accuracy over a range of computer vision tasks.
arXiv Detail & Related papers (2023-07-24T04:21:51Z) - Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
Modelling long-range dependencies is critical for scene understanding tasks in computer vision.
A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive.
We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
arXiv Detail & Related papers (2022-09-20T14:41:37Z) - Deformable Graph Transformer [31.254872949603982]
We propose Deformable Graph Transformer (DGT) that performs sparse attention with dynamically sampled key and value pairs.
Experiments demonstrate that our novel graph Transformer consistently outperforms existing Transformer-based models.
arXiv Detail & Related papers (2022-06-29T00:23:25Z) - Hybrid Model-based / Data-driven Graph Transform for Image Coding [54.31406300524195]
We present a hybrid model-based / data-driven approach to encode an intra-prediction residual block.
The first $K$ eigenvectors of a transform matrix are derived from a statistical model, e.g., the asymmetric discrete sine transform (ADST) for stability.
Using WebP as a baseline image, experimental results show that our hybrid graph transform achieved better energy compaction than default discrete cosine transform (DCT) and better stability than KLT.
arXiv Detail & Related papers (2022-03-02T15:36:44Z) - A Generalization of Transformer Networks to Graphs [5.736353542430439]
We introduce a graph transformer with four new properties compared to the standard model.
The architecture is extended to edge feature representation, which can be critical to tasks s.a. chemistry (bond type) or link prediction (entity relationship in knowledge graphs)
arXiv Detail & Related papers (2020-12-17T16:11:47Z) - Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design.
We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
arXiv Detail & Related papers (2020-10-21T20:04:22Z)
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.