834 Hits in 1.4 sec

Linked Recurrent Neural Networks [article]

Zhiwei Wang, Yao Ma, Dawei Yin, Jiliang Tang
2018 arXiv   pre-print
Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation. Most of existing RNN models have been designed for sequences assumed to be identically and independently distributed (i.i.d). However, in many real-world applications, sequences are naturally linked. For example, web documents are connected by hyperlinks; and genes
more » ... with each other. On the one hand, linked sequences are inherently not i.i.d., which poses tremendous challenges to existing RNN models. On the other hand, linked sequences offer link information in addition to the sequential information, which enables unprecedented opportunities to build advanced RNN models. In this paper, we study the problem of RNN for linked sequences. In particular, we introduce a principled approach to capture link information and propose a linked Recurrent Neural Network (LinkedRNN), which models sequential and link information coherently. We conduct experiments on real-world datasets from multiple domains and the experimental results validate the effectiveness of the proposed framework.
arXiv:1808.06170v1 fatcat:z4qdt3yofnfmfjmftj3x2gu32a

Multi-dimensional Graph Convolutional Networks [article]

Yao Ma, Suhang Wang, Charu C. Aggarwal, Dawei Yin, Jiliang Tang
2018 arXiv   pre-print
Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video. Recently, increasing attention has been paid on generalizing CNNs to graph or network data which is highly irregular. Some focus on graph-level representation learning while others aim to learn node-level representations. These methods have been shown to boost the performance of many graph-level tasks such as graph classification and node-level tasks such as
more » ... classification. Most of these methods have been designed for single-dimensional graphs where a pair of nodes can only be connected by one type of relation. However, many real-world graphs have multiple types of relations and they can be naturally modeled as multi-dimensional graphs with each type of relation as a dimension. Multi-dimensional graphs bring about richer interactions between dimensions, which poses tremendous challenges to the graph convolutional neural networks designed for single-dimensional graphs. In this paper, we study the problem of graph convolutional networks for multi-dimensional graphs and propose a multi-dimensional convolutional neural network model mGCN aiming to capture rich information in learning node-level representations for multi-dimensional graphs. Comprehensive experiments on real-world multi-dimensional graphs demonstrate the effectiveness of the proposed framework.
arXiv:1808.06099v1 fatcat:usl6wfis4raftoxqna7oclqrki

Streaming Recommender Systems [article]

Shiyu Chang, Yang Zhang, Jiliang Tang, Dawei Yin, Yi Chang, Mark A. Hasegawa-Johnson, Thomas S. Huang
2016 arXiv   pre-print
Ding and Li [8] , Koren [13] , Yin et al. [25] and Xiang et al. [23] ). Zhang et al. [26] in- vestigated the recurrence dynamics of social tagging. Xiong et al.  ... 
arXiv:1607.06182v1 fatcat:4eouzwo425aj7ewpqg5hmw23y4

Synthesis of Thiadiazole Zineb

Liu Yuting, Su baojun, Zhou Ying, Yin Dawei
2011 Procedia Engineering  
In this paper, a series of 2-amino-5-alkyl-1, 3, 4-thiadiazole zineb were prepared by reacting 2-amino-5alkyl-1, 3, 4-thiadiazole, CS 2 and ZnCl 2 . Its synthesis conditions was discussed. The optimal conditions were obtained as follows: reaction time 120 min, reaction temperature 30℃, molar ratio n (thiadiazole): n (zinc chloride): n (CS 2 ): n (NaOH) = 1:1:1.05:1.05, the products was synthesized in water. All compounds were characterized by elemental analysis, Infrared (IR)analysis to determine their structure.
doi:10.1016/j.proeng.2011.11.2688 fatcat:gs4gzb4wwnbp7ezqqykcvlgn7e

Robust Reinforcement Learning with Wasserstein Constraint [article]

Linfang Hou, Liang Pang, Xin Hong, Yanyan Lan, Zhiming Ma, Dawei Yin
2020 arXiv   pre-print
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness through disturbing the current state or simulating environmental parameters in a heuristic way, which lack quantified robustness to the system dynamics (i.e. transition probability). To overcome this issue, we leverage Wasserstein distance to measure the disturbance to the reference transition kernel. With Wasserstein
more » ... istance, we are able to connect transition kernel disturbance to the state disturbance, i.e. reduce an infinite-dimensional optimization problem to a finite-dimensional risk-aware problem. Through the derived risk-aware optimal Bellman equation, we show the existence of optimal robust policies, provide a sensitivity analysis for the perturbations, and then design a novel robust learning algorithm--Wasserstein Robust Advantage Actor-Critic algorithm (WRAAC). The effectiveness of the proposed algorithm is verified in the Cart-Pole environment.
arXiv:2006.00945v1 fatcat:zsxnk3qjvzfihdkan4i2ks6rc4

Advances in sepsis-associated liver dysfunction

Yongming Yao, Dawei Wang, Yimei Yin
2014 Burns & Trauma  
doi:10.4103/2321-3868.132689 pmid:27602369 pmcid:PMC5012093 fatcat:3ofrqffg2ncgrg5ogor7aye7ey

Geometry Contrastive Learning on Heterogeneous Graphs [article]

Shichao Zhu, Chuan Zhou, Anfeng Cheng, Shirui Pan, Shuaiqiang Wang, Dawei Yin, Bin Wang
2022 arXiv   pre-print
Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous graphs into a single geometric space, either Euclidean or hyperbolic. This kind of single geometric view is usually not enough to observe the complete picture of heterogeneous graphs due to their rich semantics and complex structures. Under these observations,
more » ... paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL), to better represent the heterogeneous graphs when supervisory data is unavailable. GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures, which is expected to bring in more benefits for downstream tasks. GCL maximizes the mutual information between two geometric views by contrasting representations at both local-local and local-global semantic levels. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines, including both unsupervised methods and supervised methods, on three tasks, including node classification, node clustering and similarity search.
arXiv:2206.12547v1 fatcat:dfjnsdw7rfcnrn3mzmvtquof3q

Graph Enhanced BERT for Query Understanding [article]

Juanhui Li, Yao Ma, Wei Zeng, Suqi Cheng, Jiliang Tang, Shuaiqiang Wang, Dawei Yin
2022 arXiv   pre-print
Query understanding plays a key role in exploring users' search intents and facilitating users to locate their most desired information. However, it is inherently challenging since it needs to capture semantic information from short and ambiguous queries and often requires massive task-specific labeled data. In recent years, pre-trained language models (PLMs) have advanced various natural language processing tasks because they can extract general semantic information from large-scale corpora.
more » ... erefore, there are unprecedented opportunities to adopt PLMs for query understanding. However, there is a gap between the goal of query understanding and existing pre-training strategies -- the goal of query understanding is to boost search performance while existing strategies rarely consider this goal. Thus, directly applying them to query understanding is sub-optimal. On the other hand, search logs contain user clicks between queries and urls that provide rich users' search behavioral information on queries beyond their content. Therefore, in this paper, we aim to fill this gap by exploring search logs. In particular, to incorporate search logs into pre-training, we first construct a query graph where nodes are queries and two queries are connected if they lead to clicks on the same urls. Then we propose a novel graph-enhanced pre-training framework, GE-BERT, which can leverage both query content and the query graph. In other words, GE-BERT can capture both the semantic information and the users' search behavioral information of queries. Extensive experiments on various query understanding tasks have demonstrated the effectiveness of the proposed framework.
arXiv:2204.06522v1 fatcat:qpj5jr7kqrad3lzrgj4rpohwxu

Streaming Graph Neural Networks [article]

Yao Ma, Ziyi Guo, Zhaochun Ren, Eric Zhao, Jiliang Tang, Dawei Yin
2018 arXiv   pre-print
Graphs are essential representations of many real-world data such as social networks. Recent years have witnessed the increasing efforts made to extend the neural network models to graph-structured data. These methods, which are usually known as the graph neural networks, have been applied to advance many graphs related tasks such as reasoning dynamics of the physical system, graph classification, and node classification. Most of the existing graph neural network models have been designed for
more » ... atic graphs, while many real-world graphs are inherently dynamic. For example, social networks are naturally evolving as new users joining and new relations being created. Current graph neural network models cannot utilize the dynamic information in dynamic graphs. However, the dynamic information has been proven to enhance the performance of many graph analytic tasks such as community detection and link prediction. Hence, it is necessary to design dedicated graph neural networks for dynamic graphs. In this paper, we propose DGNN, a new Dynamic Graph Neural Network model, which can model the dynamic information as the graph evolving. In particular, the proposed framework can keep updating node information by capturing the sequential information of edges (interactions), the time intervals between edges and information propagation coherently. Experimental results on various dynamic graphs demonstrate the effectiveness of the proposed framework.
arXiv:1810.10627v2 fatcat:gngemxlymrdj7l7oalyg35dddu

Power efficiency of time-stretch imaging system by using parallel interleaving detection

Mengxuan Lv Mengxuan Lv, Bo Dai Bo Dai, Songchao Yin Songchao Yin, Dawei Zhang Dawei Zhang, and Xu Wang and Xu Wang
2016 Chinese Optics Letters (COL)  
A 38.88 MHz time-stretch line-scan imaging system with parallel interleaving detection is experimentally demonstrated. Since only half-chromatic dispersion is used to stretch optical pulses for wavelength-to-time mapping, the power efficiency is significantly improved by 6.5 dB. Furthermore, the theoretical analysis indicates that the power loss can be efficiently reduced for scan rates less than 100 MHz. In addition, a mathematical model for signal-to-noise evaluation is derived, including
more » ... ified spontaneous emission noise in the power compensation. Thanks to the improvement of the power efficiency by using parallel interleaving detection, the signal quality is enhanced.
doi:10.3788/col201614.101103 fatcat:ddhn43xqireifnmwj4rjvk7qfy

Modeling Topical Relevance for Multi-Turn Dialogue Generation [article]

Hainan Zhang, Yanyan Lan, Liang Pang, Hongshen Chen, Zhuoye Ding, Dawei Yin
2020 arXiv   pre-print
Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly,
more » ... Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations.
arXiv:2009.12735v1 fatcat:r467p37gfjetpkmtbrd6myfkvi

Diversifying Search Results with Popular Subtopics

Dawei Yin, Zhenzhen Xue, Xiaoguang Qi, Brian D. Davison
2009 Text Retrieval Conference  
This paper describes the method we use in the diversity task of web track in TREC 2009. The problem we aim to solve is the diversification of search results for ambiguous web queries. We present a model based on knowledge of the diversity of query subtopics to generate a diversified ranking for retrieved documents. We expand the original query into several related queries, assuming that query expansions expose subtopics of the original query. Moreover, each query expansion is given a weight
more » ... h reflects the likelihood of the interpretation (the fraction of users who issued this query given the general query topic). We issue all those expanded queries including the original query to a standard BM25 search engine, then re-rank the retrieved documents to generate the final ranking. Our method can detect possible subtopics of a given query and provide a reasonable ranking that satisfies both relevancy and diversity metrics. The TREC evaluations show our method is effective on the diversity task.
dblp:conf/trec/YinXQD09 fatcat:4gec7miubfcndgvcqpqtekedj4

SceneRec: Scene-Based Graph Neural Networks for Recommender Systems [article]

Gang Wang, Ziyi Guo, Xiang Li, Dawei Yin, Shuai Ma
2021 arXiv   pre-print
Collaborative filtering has been largely used to advance modern recommender systems to predict user preference. A key component in collaborative filtering is representation learning, which aims to project users and items into a low dimensional space to capture collaborative signals. However, the scene information, which has effectively guided many recommendation tasks, is rarely considered in existing collaborative filtering methods. To bridge this gap, we focus on scene-based collaborative
more » ... mmendation and propose a novel representation model SceneRec. SceneRec formally defines a scene as a set of pre-defined item categories that occur simultaneously in real-life situations and creatively designs an item-category-scene hierarchical structure to build a scene-based graph. In the scene-based graph, we adopt graph neural networks to learn scene-specific representation on each item node, which is further aggregated with latent representation learned from collaborative interactions to make recommendations. We perform extensive experiments on real-world E-commerce datasets and the results demonstrate the effectiveness of the proposed method.
arXiv:2102.06401v1 fatcat:sztel6ajtnbqxfcagovcqb76bm

ZnO Film Photocatalysts

Bosi Yin, Siwen Zhang, Dawei Zhang, Yang Jiao, Yang Liu, Fengyu Qu, Xiang Wu
2014 Journal of Nanomaterials  
Authors' Contribution Bosi Yin and Siwen Zhang contributed equally to this work.  ... 
doi:10.1155/2014/186916 fatcat:gppxbghnlvagjdcslxvvkuz4mi

Latest Progress and Application of Mannich Reaction

Yuting Liu, Qianqian Wu, Dawei Yin, Diyang Li
2016 Youji huaxue  
Mannich reaction is very important in organic chemistry, especially plays a very important role in the synthesis of drugs. In addition, Mannich base has widespread attention because of it is more significant and specific biological activity. Mannich reaction, diastereoselectivity Mannich reaction, enantioselective Mannich reaction and the application of Mannich reaction are introduced. Finally, the development aspect of this research is brought forward.
doi:10.6023/cjoc201511024 fatcat:w7glzxuprfbkjavndf5d5ne7me
« Previous Showing results 1 — 15 out of 834 results