Deep Learning
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Critical in this context is the prior knowledge accumulated from related tasks.
Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization
Previous works have implicitly studied that FL suffers from the "client-drift" problem, which is caused by the inconsistent optimum across local clients.
Red Teaming Deep Neural Networks with Feature Synthesis Tools
We argue that this is due, in part, to a common feature of many interpretability methods: they analyze model behavior by using a particular dataset.
Auslan-Daily: Australian Sign Language Translation for Daily Communication and News
Considering different geographic regions generally have their own native sign languages, it is valuable to establish corresponding SL T datasets to support related communication and research. Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale dataset for SL T.
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant computation overhead. We observe transforming the DNN weights into circulant matrices converts general matrix-vector multiplications into HE-friendly 1-dimensional convolutions, drastically reducing the HE computation cost.
Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model
It is crucial to quantify the uncertainty of these dynamics models when using them for planning.