paper-with-me

홈 › Papers

Graph Expansion in Pruned Recurrent Neural Network Layers Preserve Performance

2024-03-17 · Suryam Arnav Kalra, Arindam Biswas, Pabitra Mitra, BISWAJIT BASU

Expansion property of a graph refers to its strong connectivity as well as sparseness. It has been reported that deep neural networks can be pruned to a high degree of sparsity while maintaining their performance. Such pruning is essential for performing real time sequence learning tasks using recurrent neural networks in resource constrained platforms. We prune recurrent networks such as RNNs and LSTMs, maintaining a large spectral gap of the underlying graphs and ensuring their layerwise expansion properties. We also study the time unfolded recurrent network graphs in terms of the properties of their bipartite layers. Experimental results for the benchmark sequence MNIST, CIFAR-10, and Google speech command data show that expander graph properties are key to preserving classification accuracy of RNN and LSTM.

📄 PDF Abstract BibTeX arXiv:2403.11100

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learning

2019-04-17 · Binxuan Huang, Kathleen M. Carley

In this paper, we study the problem of node representation learning with graph neural networks. We present a graph neural network class named recurrent graph neural network (RGNN), that address the shortcomings of prior …

Graph Neural NetworkGraph Representation LearningRepresentation Learning

SNP: Structured Neuron-level Pruning to Preserve Attention Scores

2024-04-18 · KyungHwan Shim, Jaewoong Yun, Shinkook Choi

Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which have achieved great success in various vision tasks. However, their high computational cost and memory footprint hinder their deploy…

Iterative Filter Pruning for Concatenation-based CNN Architectures

2024-05-04 · Svetlana Pavlitska, Oliver Bagge, Federico Peccia, Toghrul Mammadov 외

Model compression and hardware acceleration are essential for the resource-efficient deployment of deep neural networks. Modern object detectors have highly interconnected convolutional layers with concatenations. In thi…

Model Compression

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning

2025-07-10 · Yibo Lyu, Rui Shao, Gongwei Chen, Yijie Zhu 외 arxiv

As multimedia content expands, the demand for unified multimodal retrieval (UMR) in real-world applications increases. Recent work leverages multimodal large language models (MLLMs) to tackle this task. However, their la…

Contrastive Learning

Structural Pruning for Diffusion Models

2023-05-18 · NeurIPS 2023 11 · Gongfan Fang, Xinyin Ma, Xinchao Wang

Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, oft…