Takuya Akiba

发表

PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track pdf

Takuya Akiba, Yusuke Niitani, Tommi Kerola, 2018, ArXiv.

Computing Personalized PageRank Quickly by Exploiting Graph Structures

Takuya Akiba, Yoichi Iwata, Ken-ichi Kawarabayashi, 2014, Proc. VLDB Endow..

Fast exact shortest-path distance queries on large networks by pruned landmark labeling pdf

Takuya Akiba, Yoichi Iwata, Yuichi Yoshida, 2013, SIGMOD '13.

An Exact Algorithm for Diameters of Large Real Directed Graphs

Takuya Akiba, Yoichi Iwata, Yuki Kawata, 2015, SEA.

Cherenkov phase-matched terahertz wave generation and its spectroscopic applications

Takuya Akiba, Hirohisa Uchida, Koji Suizu, 2013, Other Conferences.

Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects

Takuya Akiba, Yusuke Niitani, Tommi Kerola, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Optuna: A Next-generation Hyperparameter Optimization Framework

Takuya Akiba, Shotaro Sano, Toshihiko Yanase, 2019, KDD.

Efficient Algorithms for Spanning Tree Centrality

Takuya Akiba, Yuichi Yoshida, Takanori Hayashi, 2016, IJCAI.

Variance-based Gradient Compression for Efficient Distributed Deep Learning pdf

Takuya Akiba, Hiroto Imachi, Yusuke Tsuzuku, 2018, ICLR.

Integer programming approach for directed minimum spanning tree problem on temporal graphs

Takuya Akiba, Takuto Ikuta, Takuya Akiba, 2016, NDA@SIGMOD.

Chainer: A Deep Learning Framework for Accelerating the Research Cycle

Takuya Akiba, Yusuke Niitani, Shunta Saito, 2019, KDD.

Compact and Scalable Graph Neighborhood Sketching

Takuya Akiba, Yosuke Yano, Takuya Akiba, 2016, KDD.

Random-Radius Ball Method for Estimating Closeness Centrality

Takuya Akiba, Yuichi Yoshida, Wataru Inariba, 2017, AAAI.

Cut Tree Construction from Massive Graphs

Takuya Akiba, Yoichi Iwata, Naoto Mizuno, 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

Fully Dynamic Shortest-Path Distance Query Acceleration on Massive Networks

Takuya Akiba, Ken-ichi Kawarabayashi, Takanori Hayashi, 2016, CIKM.

Shakedrop Regularization for Deep Residual Learning

Takuya Akiba, Masakazu Iwamura, Koichi Kise, 2018, IEEE Access.

Dynamic Influence Analysis in Evolving Networks

Takuya Akiba, Ken-ichi Kawarabayashi, Yuichi Yoshida, 2016, Proc. VLDB Endow..

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

Takuya Akiba, Gentaro Watanabe, Masanori Koyama, 2019, NeurIPS.

Shortest-path queries for complex networks: exploiting low tree-width outside the core

Takuya Akiba, Ken-ichi Kawarabayashi, Christian Sommer, 2012, EDBT '12.

Pruned labeling algorithms: fast, exact, dynamic, simple and general indexing scheme for shortest-path queries

Takuya Akiba, 2014, WWW '14 Companion.

Fractality of Massive Graphs: Scalable Analysis with Sketch-Based Box-Covering Algorithm

Takuya Akiba, Taro Takaguchi, Kenko Nakamura, 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

Branch-and-reduce exponential/FPT algorithms in practice: A case study of vertex cover pdf

Takuya Akiba, Yoichi Iwata, Takuya Akiba, 2014, Theor. Comput. Sci..

Dynamic and historical shortest-path distance queries on large evolving networks by pruned landmark labeling

Takuya Akiba, Yoichi Iwata, Yuichi Yoshida, 2014, WWW.

Linear-time enumeration of maximal K-edge-connected subgraphs in large networks by random contraction

Takuya Akiba, Yoichi Iwata, Yuichi Yoshida, 2013, CIKM.

Gauging Research in Program Synthesis with a Massive Open Online Contest

Takuya Akiba, Yoichi Iwata, Nikhil Swamy, 2014 .

Fully Dynamic Betweenness Centrality Maintenance on Massive Networks

Takuya Akiba, Yuichi Yoshida, Takanori Hayashi, 2015, Proc. VLDB Endow..

Japanese Hyponymy Extraction based on a Term Similarity Graph

Takuya Akiba, Tetsuya Sakai, 2011 .

Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes pdf

Takuya Akiba, Keisuke Fukuda, Shuji Suzuki, 2017, ArXiv.

Efficient Top-k Shortest-Path Distance Queries on Large Networks by Pruned Landmark Labeling

Takuya Akiba, Yoichi Iwata, Yuichi Yoshida, 2015, AAAI.

Calibrating Research in Program Synthesis Using 72,000 Hours of Programmer Time

Takuya Akiba, Yoichi Iwata, Nikhil Swamy, 2013 .

Adversarial Attacks and Defences Competition pdf

Yao Zhao, Takuya Akiba, Motoki Abe, 2018, ArXiv.

Fast Top- k Distance Retrieval for Network Structural Proximity Features

Takuya Akiba, Yoichi Iwata, Takanori Hayashi, 2016 .

Fast and Accurate Influence Maximization on Large Networks with Pruned Monte-Carlo Simulations

Takuya Akiba, Ken-ichi Kawarabayashi, Yuichi Yoshida, 2014, AAAI.

BDD-Constrained A ∗ Search: A Fast Method for Solving Constrained DAG Shortest-Path Problems

Takuya Akiba, Masaaki Nagata, Masaaki Nishino, 2017 .

Fast and scalable reachability queries on graphs by pruned labeling with landmarks and paths

Takuya Akiba, Yoichi Iwata, Yuichi Yoshida, 2013, CIKM.

Network structural analysis via core-tree-decomposition Publication of this article pending inquiry

Takuya Akiba, Ken-ichi Kawarabayashi, Takanori Maehara, 2014, KDD.

Hierarchical and Dynamic k-Path Covers

Takuya Akiba, Naoto Mizuno, Yosuke Yano, 2016, CIKM.

Team PFDet's Methods for Open Images Challenge 2019 pdf

Takuya Akiba, Toru Ogawa, Yusuke Niitani, 2019, ArXiv.

ChainerMN: Scalable Distributed Deep Learning Framework pdf

Takuya Akiba, Keisuke Fukuda, Shuji Suzuki, 2017, ArXiv.

MN-Core - A Highly Efficient and Scalable Approach to Deep Learning

Takuya Akiba, Y. Takatsukasa, Johannes Maximilian Kühn, 2021, 2021 Symposium on VLSI Circuits.