Path sharing and predicate evaluation for high-performance XML filtering
- Y. Diao, Mehmet Altinel, M. Franklin, H. Zhang, Peter M. Fischer
- Computer ScienceTODS
- 1 December 2003
The results show that the path sharing employed by YFilter can provide order-of-magnitude performance benefits, and two alternative techniques for extending YFilter's shared structure matching with support for value-based predicates are proposed, and the performance of these two techniques are compared.
UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification
- Andreas Hanselowski, H. Zhang, Iryna Gurevych
- Computer ScienceArXiv
- 3 September 2018
This paper presents the claim verification pipeline approach, which, according to the preliminary results, scored third in the shared task, out of 23 competing systems, and introduces two extensions to the Enhanced LSTM (ESIM).
Multi-messenger Observations of a Binary Neutron Star Merger
- B. Abbott, R. Abbott, P. Woudt
- PhysicsProceedings of Multifrequency Behaviour of High…
- 26 October 2019
On 2017 August 17 a binary neutron star coalescence candidate (later designated GW170817) with merger time 12:41:04 UTC was observed through gravitational waves by the Advanced LIGO and Advanced…
GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server
- Henggang Cui, H. Zhang, G. Ganger, Phillip B. Gibbons, E. Xing
- Computer ScienceEuropean Conference on Computer Systems
- 18 April 2016
GeePS enables a state-of-the-art single-node GPU implementation to scale well, such as to 13 times the number of training images processed per second on 16 machines (relative to the original optimized single- node code), and achieves a higher training throughput with just four GPU machines than that a state of theart CPU-only system achieves with 108 machines.
Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning
- Pinxin Long, Tingxiang Fan, X. Liao, Wenxi Liu, H. Zhang, Jia Pan
- Computer ScienceIEEE International Conference on Robotics and…
- 28 September 2017
This work presents a decentralized sensor-level collision avoidance policy for multi-robot systems, which directly maps raw sensor measurements to an agent's steering commands in terms of movement velocity and demonstrates that the learned policy can be well generalized to new scenarios that do not appear in the entire training period.
Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters
- H. Zhang, Zeyu Zheng, E. Xing
- Computer ScienceUSENIX Annual Technical Conference
- 11 June 2017
Poseidon exploits the layered model structures in DL programs to overlap communication and computation, reducing bursty network communication and is applicable to different DL frameworks by plugging Poseidon into Caffe and TensorFlow.
STAT3 regulates arginase-I in myeloid-derived suppressor cells from cancer patients.
- D. Vasquez-Dunddel, F. Pan, Y. Kim
- Biology, MedicineJournal of Clinical Investigation
- 1 April 2013
Results demonstrate that the suppressive function of arginase-I in both infiltrating and circulating MDSC is a downstream target of activated STAT3.
Turning from TF-IDF to TF-IGM for term weighting in text classification
- Kewen Chen, Zuping Zhang, J. Long, H. Zhang
- Computer ScienceExpert systems with applications
- 1 December 2016
The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding
- H. Zhang, O. Lund, M. Nielsen
- Biology, ChemistryBioinform.
- 1 May 2009
This PickPocket method is demonstrated to accurately predict MHC-peptide binding for a broad range of MHC alleles, including human and non-human species and was shown to be robust both when data is scarce and when the similarity to MHC molecules with characterized binding specificity is low.
Recurrent Topic-Transition GAN for Visual Paragraph Generation
- Xiaodan Liang, Zhiting Hu, H. Zhang, Chuang Gan, E. Xing
- Computer ScienceIEEE International Conference on Computer Vision
- 21 March 2017
A semi-supervised paragraph generative framework that is able to synthesize diverse and semantically coherent paragraph descriptions by reasoning over local semantic regions and exploiting linguistic knowledge is investigated.
...
...