6.1k citations · 6.1k across the 12 of their papers we have counts for
12 papers
Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
Han Xiao, Ziwei Wang, Zheng Zhu +2
In this paper, we propose a Shapley value based method to evaluate operation contribution (Shapley-NAS) for neural architecture search. Differentiable architecture search (DARTS) a…
Generalizable Mixed-Precision Quantization via Attribution Rank Preservation
Ziwei Wang, Han Xiao, Jiwen Lu +1
In this paper, we propose a generalizable mixed-precision quantization (GMPQ) method for efficient inference. Conventional methods require the consistency of datasets for bitwidth…
Asynchronous "Events" are Better For Motion Estimation
Yuhu Guo, Han Xiao, Yidong Chen +1
Event-based camera is a bio-inspired vision sensor that records intensity changes (called event) asynchronously in each pixel. As an instance of event-based camera, Dynamic and Act…
Robust Cascade Reconstruction by Steiner Tree Sampling
Han Xiao, Cigdem Aslay, Aristides Gionis
We consider a network where an infection cascade has taken place and a subset of infected nodes has been partially observed. Our goal is to reconstruct the underlying cascade that…
Reconstructing a cascade from temporal observations
Han Xiao, Polina Rozenshtein, Nikolaj Tatti +1
Given a subset of active nodes in a network can we re- construct the cascade that has generated these observa- tions? This is a problem that has been studied in the literature, but…
Convexification of Neural Graph
Han Xiao
Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex st…
Intelligence Graph
Han Xiao
In fact, there exist three genres of intelligence architectures: logics (e.g. \textit{Random Forest, A Searching}), neurons (e.g. \textit{CNN, LSTM}) and probabilities (e.g. \t…
NDT: Neual Decision Tree Towards Fully Functioned Neural Graph
Han Xiao
Though traditional algorithms could be embedded into neural architectures with the proposed principle of \cite{xiao2017hungarian}, the variables that only occur in the condition of…
Hungarian Layer: Logics Empowered Neural Architecture
Han Xiao, Yidong Chen, Xiaodong Shi
Neural architecture is a purely numeric framework, which fits the data as a continuous function. However, lacking of logic flow (e.g. \textit{if, for, while}), traditional algorith…
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Han Xiao, Kashif Rasul, Roland Vollgraf
We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,…
Discovering topically- and temporally-coherent events in interaction networks
Han Xiao, Polina Rozenshtein, Aristides Gionis
With the increasing use of online communication platforms, such as email, twitter, and messaging applications, we are faced with a growing amount of data that combine content (what…
On Kernel Mengerian Orientations of Line Multigraphs
Han Xiao
We present a polyhedral description of kernels in orientations of line multigraphs. Given a digraph , let denote the fractional kernel polytope defined on , and let $…