Search Results for author:
Found 11 papers, 5 papers with code
PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context
In this work, we investigate how to achieve the best task-adaptation performance and introduce PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers.
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
This capability implies that our FedCEO can effectively recover the disrupted semantic information by smoothing the global semantic space for different privacy settings and continuous training processes.
Community-Aware Efficient Graph Contrastive Learning via Personalized Self-Training
However, for unsupervised and structure-related tasks such as community detection, current GCL algorithms face difficulties in acquiring the necessary community-level information, resulting in poor performance.
Contrastive Deep Nonnegative Matrix Factorization for Community Detection
Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection, because of its better interpretability.
Ranked #1 on
Community Detection
on Pubmed
CLR: Channel-wise Lightweight Reprogramming for Continual Learning
Reprogramming parameters are task-specific and exclusive to each task, which makes our method immune to catastrophic forgetting.
Lightweight Learner for Shared Knowledge Lifelong Learning
We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel.
Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence
Real-time and robust photorealistic avatars for telepresence in AR/VR have been highly desired for enabling immersive photorealistic telepresence.
DRESS: Dynamic REal-time Sparse Subnets
The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints.
Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks
Eventually, the experiments showed that for low bit width precision, non-uniform quantization performs better than uniform, and at the same time, PoT quantization vastly reduces the computational complexity of the neural network.
Pixel Codec Avatars
Telecommunication with photorealistic avatars in virtual or augmented reality is a promising path for achieving authentic face-to-face communication in 3D over remote physical distances.
F-CAD: A Framework to Explore Hardware Accelerators for Codec Avatar Decoding
Creating virtual avatars with realistic rendering is one of the most essential and challenging tasks to provide highly immersive virtual reality (VR) experiences.
