Related papers: Covariance-Aware Goodness for Scalable Forward-For…
The model parameters of convolutional neural networks (CNNs) are determined by backpropagation (BP). In this work, we propose an interpretable feedforward (FF) design without any BP as a reference. The FF design adopts a data-centric…
Federated graph learning (FGL) enables collaborative training of graph neural networks (GNNs) across decentralized subgraphs without exposing raw data. While existing FGL methods often achieve high overall accuracy, we show that this…
Weight quantization is an effective technique to compress deep neural networks for their deployment on edge devices with limited resources. Traditional loss-aware quantization methods commonly use the quantized gradient to replace the…
Sampling-based algorithms, which eliminate ''unimportant'' computations during forward and/or back propagation (BP), offer potential solutions to accelerate neural network training. However, since sampling introduces approximations to…
We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform historical returns and marginal volatilities and how to regularise the eigenvalues of large equity…
Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many binarization methods have improved the accuracy of the model by…
Binary convolutional neural networks (BCNNs) provide a potential solution to reduce the memory requirements and computational costs associated with deep neural networks (DNNs). However, achieving a trade-off between performance and…
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…
The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels.…
Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical…
The backpropagation algorithm, despite its widespread use in neural network learning, may not accurately emulate the human cortex's learning process. Alternative strategies, such as the Forward-Forward Algorithm (FFA), offer a closer match…
This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In this work, we observe that GFlowNets tend to under-exploit the…
Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer…
Backward propagation (BP) is widely used to compute the gradients in neural network training. However, it is hard to implement BP on edge devices due to the lack of hardware and software resources to support automatic differentiation. This…
Layer-wise learning, as an alternative to global back-propagation, is easy to interpret, analyze, and it is memory efficient. Recent studies demonstrate that layer-wise learning can achieve state-of-the-art performance in image…
Gradient-based hyperparameter optimization has earned a widespread popularity in the context of few-shot meta-learning, but remains broadly impractical for tasks with long horizons (many gradient steps), due to memory scaling and gradient…
Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. However, symmetries provide fixed hard constraints on the functions a network can represent, need to be specified in advance, and…
We propose a novel weakly supervised learning segmentation based on several global constraints derived from box annotations. Particularly, we leverage a classical tightness prior to a deep learning setting via imposing a set of constraints…
Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pruning methods degrade performance by permanently removing…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…