paper-with-me

홈 › Papers

Inner Product-based Neural Network Similarity

2023-09-21 · NeurIPS 2023 11

Analyzing representational similarity among neural networks (NNs) is essential for interpreting or transferring deep models. In application scenarios where numerous NN models are learned, it becomes crucial to assess model similarities in computationally efficient ways. In this paper, we propose a new paradigm for reducing NN representational similarity to filter subspace distance. Specifically, when convolutional filters are decomposed as a linear combination of a set of filter subspace elements, denoted as filter atoms, and have those decomposed atom coefficients shared across networks, NN representational similarity can be significantly simplified as calculating the cosine distance among respective filter atoms, to achieve millions of times computation reduction over popular probing-based methods. We provide both theoretical and empirical evidence that such simplified filter subspace-based similarity preserves a strong linear correlation with other popular probing-based metrics, while being significantly more efficient to obtain and robust to probing data. We further validate the effectiveness of the proposed method in various application scenarios where numerous models exist, such as federated and continual learning as well as analyzing training dynamics. We hope our findings can help further explorations of real-time large-scale representational similarity analysis in neural networks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Neural Similarity Learning

2019-10-28 · NeurIPS 2019 12 · Weiyang Liu, Zhen Liu, James M. Rehg, Le Song

Inner product-based convolution has been the founding stone of convolutional neural networks (CNNs), enabling end-to-end learning of visual representation. By generalizing inner product with a bilinear matrix, we propose…

Few-Shot Learning

Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities

2019-02-27 · Geewook Kim, Akifumi Okuno, Kazuki Fukui, Hidetoshi Shimodaira

We propose $\textit{weighted inner product similarity}$ (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive…

Graph EmbeddingModel SelectionRepresentation Learning

Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability

2018-10-04 · Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira

We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embedding (GE). In contrast to IPS, that is lim…

Graph Embedding

Non-metric Similarity Graphs for Maximum Inner Product Search

2018-12-01 · NeurIPS 2018 12 · Stanislav Morozov, Artem Babenko

In this paper we address the problem of Maximum Inner Product Search (MIPS) that is currently the computational bottleneck in a large number of machine learning applications. While being similar to the nearest neighbor …

On the Complexity of Inner Product Similarity Join

2015-10-09 · Thomas D. Ahle, Rasmus Pagh, Ilya Razenshteyn, Francesco Silvestri

A number of tasks in classification, information retrieval, recommendation systems, and record linkage reduce to the core problem of inner product similarity join (IPS join): identifying pairs of vectors in a collection …

Information RetrievalRecommendation SystemsRetrieval