4 papers
Compute-in-Memory Attention: A Time-Domain Analog Softmax Circuit with RC-Tunable Temperature
Ankur Singh, Ashish Gautam, Shruti R. Kulkarni +1
Softmax is a key operation in Transformer attention, but its exponentiation and normalization add significant overhead in compute-in-memory (CIM) accelerators, especially when anal…
VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing
Hamed Poursiami, Shay Snyder, Guojing Cong +2
Graph classification is a fundamental task in domains ranging from molecular property prediction to materials design. While graph neural networks (GNNs) achieve strong performance…
HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
Guojing Cong, Tom Potok, Hamed Poursiami +1
We present a novel algorithm, \hdgc, that marries graph convolution with binding and bundling operations in hyperdimensional computing for transductive graph learning. For predicti…
Transductive Spiking Graph Neural Networks for Loihi
Shay Snyder, Victoria Clerico, Guojing Cong +4
Graph neural networks have emerged as a specialized branch of deep learning, designed to address problems where pairwise relations between objects are crucial. Recent advancements…