paper-with-me

Papers

Learnable Embedding Space for Efficient Neural Architecture Compression

2019-02-01 · ICLR 2019 5 · Shengcao Cao, Xiaofang Wang, Kris M. Kitani

We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search. Given a teacher network, we search for a compressed network architecture by using Bayesian Optimization (BO) with a kernel function defined over our proposed embedding space to select architectures for evaluation. We demonstrate that our search algorithm can significantly outperform various baseline methods, such as random search and reinforcement learning (Ashok et al., 2018). The compressed architectures found by our method are also better than the state-of-the-art manually-designed compact architecture ShuffleNet (Zhang et al., 2018). We also demonstrate that the learned embedding space can be transferred to new settings for architecture search, such as a larger teacher network or a teacher network in a different architecture family, without any training. Code is publicly available here: https://github.com/Friedrich1006/ESNAC .

📄 PDF Abstract BibTeX arXiv:1902.00383

Code (2)

Friedrich1006/ESNAC 공식 구현 pytorch
KlabCMU/ESNAC pytorch

Tasks

Bayesian OptimizationNeural Architecture SearchReinforcement Learning

Methods 이 논문이 사용한 방법론

Random Search Random Search replaces the exhaustive enumeration of all combinations by selecting them randomly. This can be simply applied to the discrete setting described above, but also…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Architecture Compression

2019-02-08 · Anubhav Ashok

In this paper we propose a novel approach to model compression termed Architecture Compression. Instead of operating on the weight or filter space of the network like classical model compression methods, our approach ope…

DecoderModel Compression

The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems

2025-05-16 · Petr Kasalický, Martin Spišák, Vojtěch Vančura, Daniel Bohuněk 외

Industry-scale recommender systems face a core challenge: representing entities with high cardinality, such as users or items, using dense embeddings that must be accessible during both training and inference. However, a…

Recommendation SystemsRetrieval

Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space

2025-04-20 · Yichi Zhang, Qianqian Yang

Implicit Neural Representations (INRs), also known as neural fields, have emerged as a powerful paradigm in deep learning, parameterizing continuous spatial fields using coordinate-based neural networks. In this paper, w…

AttributeDecoderKolmogorov-Arnold NetworksPICO+1

Differentiable Product Quantization for End-to-End Embedding Compression

2019-08-26 · Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases lin…

Quantization

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors

2025-10-10 · Xin Liu, Runsong Zhao, Pengcheng Huang, Xinyu Liu 외 arxiv

Context compression is an advanced technique that accelerates large language model (LLM) inference by converting long inputs into compact representations. Existing methods primarily rely on autoencoding tasks to train sp…