Multilinear Operator Networks

• URL: http://arxiv.org/abs/2401.17992v1
• Date: Wed, 31 Jan 2024 16:52:19 GMT
• Title: Multilinear Operator Networks
• Authors: Yixin Cheng, Grigorios G. Chrysos, Markos Georgopoulos, Volkan Cevher
• Abstract summary: Polynomial Networks is a class of models that does not require activation functions. We propose MONet, which relies solely on multilinear operators.
• Score: 60.7432588386185
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the remarkable capabilities of deep neural networks in image recognition, the dependence on activation functions remains a largely unexplored area and has yet to be eliminated. On the other hand, Polynomial Networks is a class of models that does not require activation functions, but have yet to perform on par with modern architectures. In this work, we aim close this gap and propose MONet, which relies solely on multilinear operators. The core layer of MONet, called Mu-Layer, captures multiplicative interactions of the elements of the input token. MONet captures high-degree interactions of the input elements and we demonstrate the efficacy of our approach on a series of image recognition and scientific computing benchmarks. The proposed model outperforms prior polynomial networks and performs on par with modern architectures. We believe that MONet can inspire further research on models that use entirely multilinear operations.

Related papers

• Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
  This paper introduces the SANE approach to weight-space learning. Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
  arXiv  Detail & Related papers  (2024-06-14T13:12:07Z)
• SENetV2: Aggregated dense layer for channelwise and global representations [0.0]
  We introduce a novel aggregated multilayer perceptron, a multi-branch dense layer, within the Squeeze residual module. This fusion enhances the network's ability to capture channel-wise patterns and have global knowledge. We conduct extensive experiments on benchmark datasets to validate the model and compare them with established architectures.
  arXiv  Detail & Related papers  (2023-11-17T14:10:57Z)
• General-Purpose Multimodal Transformer meets Remote Sensing Semantic Segmentation [35.100738362291416]
  Multimodal AI seeks to exploit complementary data sources, particularly for complex tasks like semantic segmentation. Recent trends in general-purpose multimodal networks have shown great potential to achieve state-of-the-art performance. We propose a UNet-inspired module that employs 3D convolution to encode vital local information and learn cross-modal features simultaneously.
  arXiv  Detail & Related papers  (2023-07-07T04:58:34Z)
• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• Regularization of polynomial networks for image recognition [78.4786845859205]
  Polynomial Networks (PNs) have emerged as an alternative method with a promising performance and improved interpretability. We introduce a class of PNs, which are able to reach the performance of ResNet across a range of six benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T10:05:22Z)
• AnomMAN: Detect Anomaly on Multi-view Attributed Networks [11.331030689825258]
  We propose a graph convolution-based framework, named AnomMAN, to detect Anomaly on Multi-view Attributed Networks. According to experiments on real-world datasets, AnomMAN outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2022-01-08T12:49:27Z)
• Progressive Multi-stage Interactive Training in Mobile Network for Fine-grained Recognition [8.727216421226814]
  We propose a Progressive Multi-Stage Interactive training method with a Recursive Mosaic Generator (RMG-PMSI) First, we propose a Recursive Mosaic Generator (RMG) that generates images with different granularities in different phases. Then, the features of different stages pass through a Multi-Stage Interaction (MSI) module, which strengthens and complements the corresponding features of different stages. Experiments on three prestigious fine-grained benchmarks show that RMG-PMSI can significantly improve the performance with good robustness and transferability.
  arXiv  Detail & Related papers  (2021-12-08T10:50:03Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• AdnFM: An Attentive DenseNet based Factorization Machine for CTR Prediction [11.958336595818267]
  We propose a novel model called Attentive DenseNet based Factorization Machines (AdnFM) AdnFM can extract more comprehensive deep features by using all the hidden layers from a feed-forward neural network as implicit high-order features. Experiments on two real-world datasets show that the proposed model can effectively improve the performance of Click-Through-Rate prediction.
  arXiv  Detail & Related papers  (2020-12-20T01:00:39Z)
• Evolving Normalization-Activation Layers [100.82879448303805]
  We develop efficient rejection protocols to quickly filter out candidate layers that do not work well. Our method leads to the discovery of EvoNorms, a set of new normalization-activation layers with novel, and sometimes surprising structures. Our experiments show that EvoNorms work well on image classification models including ResNets, MobileNets and EfficientNets.
  arXiv  Detail & Related papers  (2020-04-06T19:52:48Z)

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.