Fast Private Parameter Learning and Evaluation for Sum-Product Networks

• URL: http://arxiv.org/abs/2104.07353v1
• Date: Thu, 15 Apr 2021 10:21:51 GMT
• Title: Fast Private Parameter Learning and Evaluation for Sum-Product Networks
• Abstract summary: We show how to learn the weights for the sum nodes, assuming the architecture is fixed, and the data is horizontally partitioned between multiple parties. The computations will preserve the privacy of each participant. We also show how simple and private evaluations can be performed using the learned SPN.
• Score: 4.189643331553922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A sum-product network (SPN) is a graphical model that allows several types of inferences to be drawn efficiently. There are two types of learning for SPNs: Learning the architecture of the model, and learning the parameters. In this paper, we tackle the second problem: We show how to learn the weights for the sum nodes, assuming the architecture is fixed, and the data is horizontally partitioned between multiple parties. The computations will preserve the privacy of each participant. Furthermore, we will use secret sharing instead of (homomorphic) encryption, which allows fast computations and requires little computational resources. To this end, we use a novel integer division to compute approximate real divisions. We also show how simple and private evaluations can be performed using the learned SPN.

Related papers

• N-Parties Private Structure and Parameter Learning for Sum-Product Networks [5.392108098556604]
  A sum-product network (SPN) is a graphical model that allows several types of probabilistic inference to be performed efficiently.<n>We propose a privacy-preserving protocol which tackles structure generation and parameter learning of SPNs.<n>We also provide a protocol for private inference on SPNs, subsequent to training.
  arXiv  Detail & Related papers  (2025-10-07T13:55:06Z)
• Soft Learning Probabilistic Circuits [2.6436521007616114]
  This paper focuses on the main algorithm for training PCs, LearnSPN, a gold standard due to its efficiency, performance, and ease of use. We show that LearnSPN is a greedy likelihood maximizer under mild assumptions. We propose a new learning procedure named SoftLearn, that induces a PC using a soft clustering process.
  arXiv  Detail & Related papers  (2024-03-21T15:56:15Z)
• Memorization With Neural Nets: Going Beyond the Worst Case [5.03863830033243]
  In practice, deep neural networks are often able to easily interpolate their training data. We introduce a simple randomized algorithm that constructs an interpolating three-layer neural network in time. We obtain guarantees that are independent of the number of samples and hence move beyond worst-case memorization capacity bounds.
  arXiv  Detail & Related papers  (2023-09-30T10:06:05Z)
• Communication-Efficient Decentralized Federated Learning via One-Bit Compressive Sensing [52.402550431781805]
  Decentralized federated learning (DFL) has gained popularity due to its practicality across various applications. Compared to the centralized version, training a shared model among a large number of nodes in DFL is more challenging. We develop a novel algorithm based on the framework of the inexact alternating direction method (iADM)
  arXiv  Detail & Related papers  (2023-08-31T12:22:40Z)
• Neural ShDF: Reviving an Efficient and Consistent Mesh Segmentation Method [0.0]
  We present a data-driven approach leveraging deep learning to encode a mapping function prior to mesh segmentation. Our approach is resolution-agnostic as we downsample the input meshes and query the full-resolution structure.
  arXiv  Detail & Related papers  (2023-06-14T18:27:39Z)
• VertiBayes: Learning Bayesian network parameters from vertically partitioned data with missing values [2.9707233220536313]
  Federated learning makes it possible to train a machine learning model on decentralized data. We propose a novel method called VertiBayes to train Bayesian networks on vertically partitioned data. We experimentally show our approach produces models comparable to those learnt using traditional algorithms.
  arXiv  Detail & Related papers  (2022-10-31T11:13:35Z)
• Neural Attentive Circuits [93.95502541529115]
  We introduce a general purpose, yet modular neural architecture called Neural Attentive Circuits (NACs) NACs learn the parameterization and a sparse connectivity of neural modules without using domain knowledge. NACs achieve an 8x speedup at inference time while losing less than 3% performance.
  arXiv  Detail & Related papers  (2022-10-14T18:00:07Z)
• Learning Best Combination for Efficient N:M Sparsity [75.34103761423803]
  N:M learning can be naturally characterized as a problem which searches for the best combination within a finite collection. We show that our learning best combination (LBC) performs consistently better than off-the-shelf N:M sparsity methods across various networks.
  arXiv  Detail & Related papers  (2022-06-14T07:51:31Z)
• CECILIA: Comprehensive Secure Machine Learning Framework [2.949446809950691]
  We propose a secure 3-party framework, CECILIA, offering PP building blocks to enable complex operations privately. CECILIA also has two novel methods, which are the exact exponential of a public base raised to the power of a secret value and the inverse square root of a secret Gram matrix. The framework shows a great promise to make other ML algorithms as well as further computations privately computable.
  arXiv  Detail & Related papers  (2022-02-07T09:27:34Z)
• Exploring the Common Principal Subspace of Deep Features in Neural Networks [50.37178960258464]
  We find that different Deep Neural Networks (DNNs) trained with the same dataset share a common principal subspace in latent spaces. Specifically, we design a new metric $mathcalP$-vector to represent the principal subspace of deep features learned in a DNN. Small angles (with cosine close to $1.0$) have been found in the comparisons between any two DNNs trained with different algorithms/architectures.
  arXiv  Detail & Related papers  (2021-10-06T15:48:32Z)
• Solving Mixed Integer Programs Using Neural Networks [57.683491412480635]
  This paper applies learning to the two key sub-tasks of a MIP solver, generating a high-quality joint variable assignment, and bounding the gap in objective value between that assignment and an optimal one. Our approach constructs two corresponding neural network-based components, Neural Diving and Neural Branching, to use in a base MIP solver such as SCIP. We evaluate our approach on six diverse real-world datasets, including two Google production datasets and MIPLIB, by training separate neural networks on each.
  arXiv  Detail & Related papers  (2020-12-23T09:33:11Z)
• Training Deep Neural Networks with Constrained Learning Parameters [4.917317902787792]
  A significant portion of deep learning tasks would run on edge computing systems. We propose the Combinatorial Neural Network Training Algorithm (CoNNTrA) CoNNTrA trains deep learning models with ternary learning parameters on the MNIST, Iris and ImageNet data sets. Our results indicate that CoNNTrA models use 32x less memory and have errors at par with the Backpropagation models.
  arXiv  Detail & Related papers  (2020-09-01T16:20:11Z)
• ResNeSt: Split-Attention Networks [86.25490825631763]
  We present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification.
  arXiv  Detail & Related papers  (2020-04-19T20:40:31Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

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.