79 citations · 355 across the 59 of their papers we have counts for
14 papers · 1 filter
Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
Xiwen Wei, Mustafa Munir, Radu Marculescu
Unified Multimodal Generative Models (UMGMs) unify visual understanding and image generation within a single autoregressive framework. However, their ability to continually learn n…
Single-Round Scalable Analytic Federated Learning
Alan T. L. Bacellar, Mustafa Munir, Felipe M. G. França +3
Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-…
Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devices
Hiroki Matsutani, Masaaki Kondo, Kazuki Sunaga +1
This paper proposes Skip2-LoRA as a lightweight fine-tuning method for deep neural networks to address the gap between pre-trained and deployed models. In our approach, trainable L…
A Tiny Supervised ODL Core with Auto Data Pruning for Human Activity Recognition
Hiroki Matsutani, Radu Marculescu
In this paper, we introduce a low-cost and low-power tiny supervised on-device learning (ODL) core that can address the distributional shift of input data for human activity recogn…
Machine Unlearning for Image-to-Image Generative Models
Guihong Li, Hsiang Hsu, Chun-Fu Chen +1
Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlea…
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models
Guihong Li, Hsiang Hsu, Chun-Fu Chen +1
The rapid growth of machine learning has spurred legislative initiatives such as ``the Right to be Forgotten,'' allowing users to request data removal. In response, ``machine unlea…
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities
Guihong Li, Duc Hoang, Kartikeya Bhardwaj +3
Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process. The key idea behind zero-…
TIPS: Topologically Important Path Sampling for Anytime Neural Networks
Guihong Li, Kartikeya Bhardwaj, Yuedong Yang +1
Anytime neural networks (AnytimeNNs) are a promising solution to adaptively adjust the model complexity at runtime under various hardware resource constraints. However, the manuall…
ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients
Guihong Li, Yuedong Yang, Kartikeya Bhardwaj +1
Neural Architecture Search (NAS) is widely used to automatically obtain the neural network with the best performance among a large number of candidate architectures. To reduce the…
SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning
Zihui Xue, Yuedong Yang, Mengtian Yang +1
Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Neve…
FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning
Wei Chen, Kartikeya Bhardwaj, Radu Marculescu
In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i.e., data being non-IID) across multipl…
EdgeAI: A Vision for Deep Learning in IoT Era
Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu
The significant computational requirements of deep learning present a major bottleneck for its large-scale adoption on hardware-constrained IoT-devices. Here, we envision a new par…
On Network Science and Mutual Information for Explaining Deep Neural Networks
Brian Davis, Umang Bhatt, Kartikeya Bhardwaj +2
In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforwar…
Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande +2
Tight collaboration between experts of machine learning and manycore system design is necessary to create a data-driven manycore design framework that integrates both learning and…