Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
- URL: http://arxiv.org/abs/2112.06281v1
- Date: Sun, 12 Dec 2021 17:13:14 GMT
- Title: Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
- Authors: Shiye Lei, Zhuozhuo Tu, Leszek Rutkowski, Feng Zhou, Li Shen,
Fengxiang He and Dacheng Tao
- Abstract summary: We design a spatial-temporal-fusion BNN for efficiently scaling BNNs to large models.
Compared to vanilla BNNs, our approach can greatly reduce the training time and the number of parameters, which contributes to scale BNNs efficiently.
- Score: 77.78479877473899
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Bayesian neural networks (BNNs) have become a principal approach to alleviate
overconfident predictions in deep learning, but they often suffer from scaling
issues due to a large number of distribution parameters. In this paper, we
discover that the first layer of a deep network possesses multiple disparate
optima when solely retrained. This indicates a large posterior variance when
the first layer is altered by a Bayesian layer, which motivates us to design a
spatial-temporal-fusion BNN (STF-BNN) for efficiently scaling BNNs to large
models: (1) first normally train a neural network from scratch to realize fast
training; and (2) the first layer is converted to Bayesian and inferred by
employing stochastic variational inference, while other layers are fixed.
Compared to vanilla BNNs, our approach can greatly reduce the training time and
the number of parameters, which contributes to scale BNNs efficiently. We
further provide theoretical guarantees on the generalizability and the
capability of mitigating overconfidence of STF-BNN. Comprehensive experiments
demonstrate that STF-BNN (1) achieves the state-of-the-art performance on
prediction and uncertainty quantification; (2) significantly improves
adversarial robustness and privacy preservation; and (3) considerably reduces
training time and memory costs.
Related papers
- Bayesian Neural Networks with Domain Knowledge Priors [52.80929437592308]
We propose a framework for integrating general forms of domain knowledge into a BNN prior.
We show that BNNs using our proposed domain knowledge priors outperform those with standard priors.
arXiv Detail & Related papers (2024-02-20T22:34:53Z) - Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty
from Pre-trained Models [40.38541033389344]
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification.
We introduce the Adaptable Bayesian Neural Network (ABNN), a simple and scalable strategy to seamlessly transform DNNs into BNNs.
We conduct extensive experiments across multiple datasets for image classification and semantic segmentation tasks, and our results demonstrate that ABNN achieves state-of-the-art performance.
arXiv Detail & Related papers (2023-12-23T16:39:24Z) - Sparsifying Bayesian neural networks with latent binary variables and
normalizing flows [10.865434331546126]
We will consider two extensions to the latent binary Bayesian neural networks (LBBNN) method.
Firstly, by using the local reparametrization trick (LRT) to sample the hidden units directly, we get a more computationally efficient algorithm.
More importantly, by using normalizing flows on the variational posterior distribution of the LBBNN parameters, the network learns a more flexible variational posterior distribution than the mean field Gaussian.
arXiv Detail & Related papers (2023-05-05T09:40:28Z) - Recurrent Bilinear Optimization for Binary Neural Networks [58.972212365275595]
BNNs neglect the intrinsic bilinear relationship of real-valued weights and scale factors.
Our work is the first attempt to optimize BNNs from the bilinear perspective.
We obtain robust RBONNs, which show impressive performance over state-of-the-art BNNs on various models and datasets.
arXiv Detail & Related papers (2022-09-04T06:45:33Z) - Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks [55.531896312724555]
Bayesian Networks (BNNs) are robust and adept at handling adversarial attacks by incorporating randomness.
We create our BNN model, called BNN-DenseNet, by fusing Bayesian inference (i.e., variational Bayes) to the DenseNet architecture.
An adversarially-trained BNN outperforms its non-Bayesian, adversarially-trained counterpart in most experiments.
arXiv Detail & Related papers (2021-11-16T16:14:44Z) - S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural
Networks via Guided Distribution Calibration [74.5509794733707]
We present a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution.
Our proposed method can boost the simple contrastive learning baseline by an absolute gain of 5.515% on BNNs.
Our method achieves substantial improvement over the simple contrastive learning baseline, and is even comparable to many mainstream supervised BNN methods.
arXiv Detail & Related papers (2021-02-17T18:59:28Z) - Going Deeper With Directly-Trained Larger Spiking Neural Networks [20.40894876501739]
Spiking neural networks (SNNs) are promising in coding for bio-usible information and event-driven signal processing.
However, the unique working mode of SNNs makes them more difficult to train than traditional networks.
We propose a CIF-dependent batch normalization (tpladBN) method based on the emerging-temporal backproation threshold.
arXiv Detail & Related papers (2020-10-29T07:15:52Z) - FATNN: Fast and Accurate Ternary Neural Networks [89.07796377047619]
Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts.
In this work, we show that, under some mild constraints, computational complexity of the ternary inner product can be reduced by a factor of 2.
We elaborately design an implementation-dependent ternary quantization algorithm to mitigate the performance gap.
arXiv Detail & Related papers (2020-08-12T04:26:18Z) - T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding [26.654533157221973]
This paper introduces the concept of time-to-first-spike coding into deep SNNs using the kernel-based dynamic threshold and dendrite to overcome the drawback.
According to our results, the proposed methods can reduce inference latency and number of spikes to 22% and less than 1%, compared to those of burst coding.
arXiv Detail & Related papers (2020-03-26T04:39:12Z)
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.