activity
20182025
most citedCentroid Transformers: Learning to Abstract with Attention

20 citations · 50 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20221 cited

How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity

Chengyue Gong, Lemeng Wu, Qiang Liu

Although traditional optimization methods focus on finding a single optimal solution, most objective functions in modern machine learning problems, especially those in deep learnin…

cs.LG202120 cited

Centroid Transformers: Learning to Abstract with Attention

Lemeng Wu, Xingchao Liu, Qiang Liu

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise rel…

cs.LG2021

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

Lemeng Wu, Bo Liu, Peter Stone +1

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and archi…

cs.LG20203 cited

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough

Mao Ye, Lemeng Wu, Qiang Liu

Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size. However, the theo…

cs.LG201919 cited

Splitting Steepest Descent for Growing Neural Architectures

Qiang Liu, Lemeng Wu, Dilin Wang

We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs. By leveraging a f…

cs.LG2019

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent

Dilin Wang, Meng Li, Lemeng Wu +2

Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are h…