arXiv subjects

Hongwei Wang

Publications and source records attributed to Hongwei Wang.

At least 163 records · Page 9Linked to original sources

arXiv2019

Lipschitz Generative Adversarial Nets

In this paper, we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function. We show that GANs without restriction on the discriminative function space commonly suffer from the problem that the gradient produced by the discriminator is uninformative to guide the generator. By contrast, Wasserstein GAN (WGAN), where the discriminative function is restricted to 1-Lipschitz, does not suffer from such a gradient uninformativeness problem. We further show in the paper that the model with a compact dual form of Wasserstein distance, where the Lipschitz condition is relaxed, may also theoretically suffer from this issue. This implies the importance of Lipschitz condition and motivates us to study the general formulation of GANs with Lipschitz constraint, which leads to a new family of GANs that we call Lipschitz GANs (LGANs). We show that LGANs guarantee the existence and uniqueness of the optimal discriminative function as well as the existence of a unique Nash equilibrium. We prove that LGANs are generally capable of eliminating the gradient uninformativeness problem. According to our empirical analysis, LGANs are more stable and generate consistently higher quality samples compared with WGAN.

cs.LG↗

arXiv2019

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

Knowledge graphs capture structured information and relations between a set of entities or items. As such knowledge graphs represent an attractive source of information that could help improve recommender systems. However, existing approaches in this domain rely on manual feature engineering and do not allow for an end-to-end training. Here we propose Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) to provide better recommendations. Conceptually, our approach computes user-specific item embeddings by first applying a trainable function that identifies important knowledge graph relationships for a given user. This way we transform the knowledge graph into a user-specific weighted graph and then apply a graph neural network to compute personalized item embeddings. To provide better inductive bias, we rely on label smoothness assumption, which posits that adjacent items in the knowledge graph are likely to have similar user relevance labels/scores. Label smoothness provides regularization over the edge weights and we prove that it is equivalent to a label propagation scheme on a graph. We also develop an efficient implementation that shows strong scalability with respect to the knowledge graph size. Experiments on four datasets show that our method outperforms state of the art baselines. KGNN-LS also achieves strong performance in cold-start scenarios where user-item interactions are sparse.

cs.LG↗

arXiv2019

Data Driven Charge Transfer Atlas Provides Topological View of Electronic Structure Properties for Arbitrary Proteins Complexes

Due to the highly complex chemical structure of biomolecules, the extensive understanding of the electronic information for proteomics can be challenging. Here, we constructed a charge transfer database at residue level derived from millions of electronic structure calculations among 20x20 possible amino acid side-chains combinations, which were extracted from available high-quality structures of thousands of protein complexes. Then, the data driven network (D2Net) analysis was proposed to quickly identify the critical residue or residue groups for any possible protein complex. As an initial evaluation, we applied this model to scrutinize the charge transfer networks for two randomly selected proteins, which highlighted the most critical residues with large node degrees as network hubs. This work may provide us a promising computional protocol for topologically understanding the electronic structure information in the growing number of high-quality experimental proteins structures, with minor computational costs.

physics.chem-ph↗

arXiv2019

PandaX-II Constraints on Spin-Dependent WIMP-Nucleon Effective Interactions

We present PandaX-II constraints on candidate WIMP-nucleon effective interactions involving the nucleon or WIMP spin, including, in addition to standard axial spin-dependent (SD) scattering, various couplings among vector and axial currents, magnetic and electric dipole moments, and tensor interactions. The data set corresponding to a total exposure of 54-ton-days is reanalyzed to determine constraints as a function of the WIMP mass and isospin coupling. We obtain WIMP-nucleon cross section bounds of $\rm 1.6 \times 10^{-41} cm^2$ and $\rm 9.0 \times 10^{-42} cm^2$ ($90\%$ c.l.) for neutron-only SD and tensor coupling, respectively, for a mass $M_\mathrm{WIMP} \sim {\rm 40~GeV}/c^2$. The SD limits are the best currently available for $M_\mathrm{WIMP} > {\rm 40~GeV}/c^2$. We show that PandaX-II has reached a sensitivity sufficient to probe a variety of other candidate spin-dependent interactions at the weak scale.

hep-ex↗

arXiv2019

Knowledge Graph Convolutional Networks for Recommender Systems

To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information. In general, the attributes are not isolated but connected with each other, which forms a knowledge graph (KG). In this paper, we propose Knowledge Graph Convolutional Networks (KGCN), an end-to-end framework that captures inter-item relatedness effectively by mining their associated attributes on the KG. To automatically discover both high-order structure information and semantic information of the KG, we sample from the neighbors for each entity in the KG as their receptive field, then combine neighborhood information with bias when calculating the representation of a given entity. The receptive field can be extended to multiple hops away to model high-order proximity information and capture users' potential long-distance interests. Moreover, we implement the proposed KGCN in a minibatch fashion, which enables our model to operate on large datasets and KGs. We apply the proposed model to three datasets about movie, book, and music recommendation, and experiment results demonstrate that our approach outperforms strong recommender baselines.

cs.IR↗

arXiv2019

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems. In this paper, we consider knowledge graphs as the source of side information. We propose MKR, a Multi-task feature learning approach for Knowledge graph enhanced Recommendation. MKR is a deep end-to-end framework that utilizes knowledge graph embedding task to assist recommendation task. The two tasks are associated by cross&compress units, which automatically share latent features and learn high-order interactions between items in recommender systems and entities in the knowledge graph. We prove that cross&compress units have sufficient capability of polynomial approximation, and show that MKR is a generalized framework over several representative methods of recommender systems and multi-task learning. Through extensive experiments on real-world datasets, we demonstrate that MKR achieves substantial gains in movie, book, music, and news recommendation, over state-of-the-art baselines. MKR is also shown to be able to maintain a decent performance even if user-item interactions are sparse.

cs.IR↗

arXiv2018

Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets

In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs. We study the property of the optimal discriminative function and show that in many GANs, the gradient from the optimal discriminative function is not reliable, which turns out to be the fundamental cause of failure in training of GANs. We further demonstrate that a well-defined distance metric does not necessarily guarantee the convergence of GANs. Finally, we prove in this paper that Lipschitz-continuity condition is a general solution to make the gradient of the optimal discriminative function reliable, and characterized the necessary condition where Lipschitz-continuity ensures the convergence, which leads to a broad family of valid GAN objectives under Lipschitz-continuity condition, where Wasserstein distance is one special case. We experiment with several new objectives, which are sound according to our theorems, and we found that, compared with Wasserstein distance, the outputs of the discriminator with new objectives are more stable and the final qualities of generated samples are also consistently higher than those produced by Wasserstein distance.

cs.LG↗

arXiv2018

Visual-Texual Emotion Analysis with Deep Coupled Video and Danmu Neural Networks

User emotion analysis toward videos is to automatically recognize the general emotional status of viewers from the multimedia content embedded in the online video stream. Existing works fall in two categories: 1) visual-based methods, which focus on visual content and extract a specific set of features of videos. However, it is generally hard to learn a mapping function from low-level video pixels to high-level emotion space due to great intra-class variance. 2) textual-based methods, which focus on the investigation of user-generated comments associated with videos. The learned word representations by traditional linguistic approaches typically lack emotion information and the global comments usually reflect viewers' high-level understandings rather than instantaneous emotions. To address these limitations, in this paper, we propose to jointly utilize video content and user-generated texts simultaneously for emotion analysis. In particular, we introduce exploiting a new type of user-generated texts, i.e., "danmu", which are real-time comments floating on the video and contain rich information to convey viewers' emotional opinions. To enhance the emotion discriminativeness of words in textual feature extraction, we propose Emotional Word Embedding (EWE) to learn text representations by jointly considering their semantics and emotions. Afterwards, we propose a novel visual-textual emotion analysis model with Deep Coupled Video and Danmu Neural networks (DCVDN), in which visual and textual features are synchronously extracted and fused to form a comprehensive representation by deep-canonically-correlated-autoencoder-based multi-view learning. Through extensive experiments on a self-crawled real-world video-danmu dataset, we prove that DCVDN significantly outperforms the state-of-the-art baselines.

cs.CV↗

arXiv2018

Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks

Recurrent Neural Networks (RNNs) have been widely used in processing natural language tasks and achieve huge success. Traditional RNNs usually treat each token in a sentence uniformly and equally. However, this may miss the rich semantic structure information of a sentence, which is useful for understanding natural languages. Since semantic structures such as word dependence patterns are not parameterized, it is a challenge to capture and leverage structure information. In this paper, we propose an improved variant of RNN, Multi-Channel RNN (MC-RNN), to dynamically capture and leverage local semantic structure information. Concretely, MC-RNN contains multiple channels, each of which represents a local dependence pattern at a time. An attention mechanism is introduced to combine these patterns at each step, according to the semantic information. Then we parameterize structure information by adaptively selecting the most appropriate connection structures among channels. In this way, diverse local structures and dependence patterns in sentences can be well captured by MC-RNN. To verify the effectiveness of MC-RNN, we conduct extensive experiments on typical natural language processing tasks, including neural machine translation, abstractive summarization, and language modeling. Experimental results on these tasks all show significant improvements of MC-RNN over current top systems.

cs.CL↗

arXiv2018

Maximum Correntropy Derivative-Free Robust Kalman Filter and Smoother

We consider the problem of robust estimation involving filtering and smoothing for nonlinear state space models which are disturbed by heavy-tailed impulsive noises. To deal with heavy-tailed noises and improve the robustness of the traditional nonlinear Gaussian Kalman filter and smoother, we propose in this work a general framework of robust filtering and smoothing, which adopts a new maximum correntropy criterion to replace the minimum mean square error for state estimation. To facilitate understanding, we present our robust framework in conjunction with the cubature Kalman filter and smoother. A half-quadratic optimization method is utilized to solve the formulated robust estimation problems, which leads to a new maximum correntropy derivative-free robust Kalman filter and smoother. Simulation results show that the proposed methods achieve a substantial performance improvement over the conventional and existing robust ones with slight computational time increase.

stat.AP↗

arXiv2018

RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems

To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose Ripple Network, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the surface of water, Ripple Network stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user's potential interests along links in the knowledge graph. The multiple "ripples" activated by a user's historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that Ripple Network achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.

cs.IR↗

arXiv2018

Constraining Dark Matter Models with a Light Mediator from PandaX-II Experiment

We search for nuclear recoil signals of dark matter models with a light mediator in PandaX-II, a direct detection experiment in China Jinping underground Laboratory. Using data collected in 2016 and 2017 runs, corresponding to a total exposure of 54 ton day, we set upper limits on the zero-momentum dark matter-nucleon cross section. These limits have a strong dependence on the mediator mass when it is comparable to or below the typical momentum transfer. We apply our results to constrain self-interacting dark matter models with a light mediator mixing with standard model particles, and set strong limits on the model parameter space for the dark matter mass ranging from $5~{\rm GeV}$ to $10~{\rm TeV}$.

hep-ph↗

arXiv2018

Dark matter direct search sensitivity of the PandaX-4T experiment

The PandaX-4T experiment, a four-ton scale dark matter direct detection experiment, is being planned at the China Jinping Underground Laboratory. In this paper we present a simulation study of the expected background in this experiment. In a 2.8-ton fiducial mass and the signal region between 1 to 10 keV electron equivalent energy, the total electron recoil background is found to be 4.9x10^{-5} /(kg day keV). The nuclear recoil background in the same region is 2.8x10^{-7}/(kg day keV). With an exposure of 5.6 ton-years, the sensitivity of PandaX-4T could reach a minimum spin-independent dark matter-nucleon cross section of 6x10^{-48} cm^{2} at a dark matter mass of 40 GeV/c^{2}.

physics.ins-det↗

arXiv2018

Charge Transfer Database for Bio-molecule Tight Binding Model Derived from Thousands of Proteins

The anisotropic feature of charge transfer reactions in realistic proteins cannot be ignored, due to the highly complex chemical structure of bio-molecules. In this work, we have performed the first large-scale quantitative assessment of charge transfer preference in protein complexes by calculating the charge transfer couplings in all 20*20 possible amino acid side chain combinations, which are extracted from available high-quality structures of thousands of protein complexes. The charge transfer database quantitatively shows distinct features of charge transfer couplings among millions of amino acid side-chains combinations. The knowledge graph of charge transfer couplings reveals that only one average or representative structure cannot be regarded as the typical charge transfer preference in realistic proteins. This data driven model provides us an alternative route to comprehensively understand the pairwise charge transfer coupling parameters based structural similarity, without any require of the knowledge of chemical intuition about the chemical interactions.

physics.chem-ph↗

arXiv2018

DKN: Deep Knowledge-Aware Network for News Recommendation

Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent knowledge-level connections among news. The recommended results for a user are consequently limited to simple patterns and cannot be extended reasonably. Moreover, news recommendation also faces the challenges of high time-sensitivity of news and dynamic diversity of users' interests. To solve the above problems, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation. DKN is a content-based deep recommendation framework for click-through rate prediction. The key component of DKN is a multi-channel and word-entity-aligned knowledge-aware convolutional neural network (KCNN) that fuses semantic-level and knowledge-level representations of news. KCNN treats words and entities as multiple channels, and explicitly keeps their alignment relationship during convolution. In addition, to address users' diverse interests, we also design an attention module in DKN to dynamically aggregate a user's history with respect to current candidate news. Through extensive experiments on a real online news platform, we demonstrate that DKN achieves substantial gains over state-of-the-art deep recommendation models. We also validate the efficacy of the usage of knowledge in DKN.

stat.ML↗

arXiv2017

Simulation of Physical Parameters for a Photoneutron Source

A compact photoneutron source (PNS), based on an electron linac was designed and constructed to provide required nuclear data for the design of Thorium Molten Salt Reactor (TMSR). Many local shielding are built to reduce the background of neutron and γ rays, making the location of the time of flight (TOF) detector be fixed at 6.2 m place. Under the existing layout, some physical parameters are very difficult to get by the experiments, while can be obtained by the Monte Carlo simulation method. However, for the deep penetration problem of the neutron and γ rays transport in the channel of PNS with complex geometry, the normal Monte Carlo method is inefficient since electron transport calculation need a large amount of computing time and neutrons have little contribution to the detector in far-source region. In this work, the subsection method is applied in the simulation for PNS, which divide the simulation process in two steps, recording the neutron and γ rays information passing through the source window in the first step and adopting the covariance reduction techniques in the second step. The simulated neutron flux and energy spectrum at the TOF detector place with the relative error 1.6% are well agreement with the experimental results, achieving an efficiency 23 times better than the normal method. This method is fast and efficient in predicting the physical parameters, providing a required verification and initiating the foreseen physics experiment.

physics.comp-ph↗

arXiv2017

Joint Topic-Semantic-aware Social Recommendation for Online Voting

Online voting is an emerging feature in social networks, in which users can express their attitudes toward various issues and show their unique interest. Online voting imposes new challenges on recommendation, because the propagation of votings heavily depends on the structure of social networks as well as the content of votings. In this paper, we investigate how to utilize these two factors in a comprehensive manner when doing voting recommendation. First, due to the fact that existing text mining methods such as topic model and semantic model cannot well process the content of votings that is typically short and ambiguous, we propose a novel Topic-Enhanced Word Embedding (TEWE) method to learn word and document representation by jointly considering their topics and semantics. Then we propose our Joint Topic-Semantic-aware social Matrix Factorization (JTS-MF) model for voting recommendation. JTS-MF model calculates similarity among users and votings by combining their TEWE representation and structural information of social networks, and preserves this topic-semantic-social similarity during matrix factorization. To evaluate the performance of TEWE representation and JTS-MF model, we conduct extensive experiments on real online voting dataset. The results prove the efficacy of our approach against several state-of-the-art baselines.

stat.ML↗

arXiv2017

SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction

In online social networks people often express attitudes towards others, which forms massive sentiment links among users. Predicting the sign of sentiment links is a fundamental task in many areas such as personal advertising and public opinion analysis. Previous works mainly focus on textual sentiment classification, however, text information can only disclose the "tip of the iceberg" about users' true opinions, of which the most are unobserved but implied by other sources of information such as social relation and users' profile. To address this problem, in this paper we investigate how to predict possibly existing sentiment links in the presence of heterogeneous information. First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users' sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method. Then we propose a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users' latent representations from heterogeneous networks and predict the sign of unobserved sentiment links. SHINE utilizes multiple deep autoencoders to map each user into a low-dimension feature space while preserving the network structure. We demonstrate the superiority of SHINE over state-of-the-art baselines on link prediction and node recommendation in two real-world datasets. The experimental results also prove the efficacy of SHINE in cold start scenario.

stat.ML↗