Search arXiv⌕ Search

arXiv subjects

Wei Wei

Publications and source records attributed to Wei Wei.

At least 379 records · Page 21Linked to original sources
arXiv2021

Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection

The development of reusable artificial intelligence (AI) models for wider use and rigorous validation by the community promises to unlock new opportunities in multi-messenger astrophysics. Here we develop a workflow that connects the Data and Learning Hub for Science, a repository for publishing AI models, with the Hardware Accelerated Learning (HAL) cluster, using funcX as a universal distributed computing service. Using this workflow, an ensemble of four openly available AI models can be run on HAL to process an entire month's worth (August 2017) of advanced Laser Interferometer Gravitational-Wave Observatory data in just seven minutes, identifying all four all four binary black hole mergers previously identified in this dataset and reporting no misclassifications. This approach combines advances in AI, distributed computing, and scientific data infrastructure to open new pathways to conduct reproducible, accelerated, data-driven discovery.

gr-qc↗
arXiv2021

Gagliardo-Nirenberg inequalities in Lorentz type spaces and energy equality for the Navier-Stokes system

In this paper, we derive some new Gagliardo-Nirenberg type inequalities in Lorentz type spaces without restrictions on the second index of Lorentz norms, which generalize almost all known corresponding results. Our proof mainly relies on the Bernstein inequalities in Lorentz spaces, the embedding relation among various Lorentz type spaces, and Littlewood-Paley decomposition techniques. In addition, we establish several novel criteria in terms of the velocity or the gradient of the velocity in Lorentz spaces for energy conservation of the 3D Navier-Stokes equations. Particularly, we improve the classical Shinbrot's condition for energy balance to allow both the space-time directions of the velocity to be in Lorentz spaces.

math.AP↗
arXiv2021

Overcoming Catastrophic Forgetting by Generative Regularization

In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general framework for continual learning. We could further construct a generative regularization term for all given classification models by leveraging energy-based models and Langevin-dynamic sampling to enrich the features learned in each task. By combining discriminative and generative loss together, we empirically show that the proposed method outperforms state-of-the-art methods on a variety of tasks, avoiding catastrophic forgetting in continual learning. In particular, the proposed method outperforms baseline methods over 15% on the Fashion-MNIST dataset and 10% on the CUB dataset

cs.LG↗
arXiv2021

Bias-dependent intrinsic RF thermal noise modeling and characterization of single layer graphene FETs

In this article, the bias-dependence of intrinsic channel thermal noise of single-layer graphene field-effect transistors (GFETs) is thoroughly investigated by experimental observations and compact modeling. The findings indicate an increase of the specific noise as drain current increases whereas a saturation trend is observed at very high carrier density regime. Besides, short-channel effects like velocity saturation also result in an increment of noise at higher electric fields. The main goal of this work is to propose a physics-based compact model that accounts for and accurately predicts the above experimental observations in short-channel GFETs. In contrast to long-channel MOSFET based models adopted previously to describe thermal noise in graphene devices without considering the degenerate nature of graphene, in this work a model for short-channel GFETs embracing the 2D materials underlying physics and including a bias dependency is presented. The implemented model is validated with de-embedded high frequency data from two short-channel devices at Quasi-Static region of operation. The model precisely describes the experimental data for a wide range of low to high drain current values without the need of any fitting parameter. Moreover, the consideration of the degenerate nature of graphene reveals a significant decrease of noise in comparison with the non degenerate case and the model accurately captures this behavior. This work can also be of outmost significance from circuit designers aspect, since noise excess factor, a very important figure of merit for RF circuits implementation, is defined and characterized for the first time in graphene transistors.

cond-mat.mes-hall↗
arXiv2021

Global Context Enhanced Graph Neural Networks for Session-based Recommendation

Session-based recommendation (SBR) is a challenging task, which aims at recommending items based on anonymous behavior sequences. Almost all the existing solutions for SBR model user preference only based on the current session without exploiting the other sessions, which may contain both relevant and irrelevant item-transitions to the current session. This paper proposes a novel approach, called Global Context Enhanced Graph Neural Networks (GCE-GNN) to exploit item transitions over all sessions in a more subtle manner for better inferring the user preference of the current session. Specifically, GCE-GNN learns two levels of item embeddings from session graph and global graph, respectively: (i) Session graph, which is to learn the session-level item embedding by modeling pairwise item-transitions within the current session; and (ii) Global graph, which is to learn the global-level item embedding by modeling pairwise item-transitions over all sessions. In GCE-GNN, we propose a novel global-level item representation learning layer, which employs a session-aware attention mechanism to recursively incorporate the neighbors' embeddings of each node on the global graph. We also design a session-level item representation learning layer, which employs a GNN on the session graph to learn session-level item embeddings within the current session. Moreover, GCE-GNN aggregates the learnt item representations in the two levels with a soft attention mechanism. Experiments on three benchmark datasets demonstrate that GCE-GNN outperforms the state-of-the-art methods consistently.

cs.IR↗
arXiv2021

Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

cs.CL↗
arXiv2021

Exploiting Global Contextual Information for Document-level Named Entity Recognition

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential global context, which is useful especially when local context information is limited or ambiguous. To this end, we propose a model called Global Context enhanced Document-level NER (GCDoc) to leverage global contextual information from two levels, i.e., both word and sentence. At word-level, a document graph is constructed to model a wider range of dependencies between words, then obtain an enriched contextual representation for each word via graph neural networks (GNN). To avoid the interference of noise information, we further propose two strategies. First we apply the epistemic uncertainty theory to find out tokens whose representations are less reliable, thereby helping prune the document graph. Then a selective auxiliary classifier is proposed to effectively learn the weight of edges in document graph and reduce the importance of noisy neighbour nodes. At sentence-level, for appropriately modeling wider context beyond single sentence, we employ a cross-sentence module which encodes adjacent sentences and fuses it with the current sentence representation via attention and gating mechanisms. Extensive experiments on two benchmark NER datasets (CoNLL 2003 and Ontonotes 5.0 English dataset) demonstrate the effectiveness of our proposed model. Our model reaches F1 score of 92.22 (93.40 with BERT) on CoNLL 2003 dataset and 88.32 (90.49 with BERT) on Ontonotes 5.0 dataset, achieving new state-of-the-art performance.

cs.CL↗
arXiv2021

Exploring Global Information for Session-based Recommendation

Session-based recommendation (SBR) is a challenging task, which aims at recommending items based on anonymous behavior sequences. Most existing SBR studies model the user preferences based only on the current session while neglecting the item-transition information from the other sessions, which suffer from the inability of modeling the complicated item-transition pattern. To address the limitations, we introduce global item-transition information to strength the modeling of the dynamic item-transition. For fully exploiting the global item-transition information, two ways of exploring global information for SBR are studied in this work. Specifically, we first propose a basic GNN-based framework (BGNN), which solely uses session-level item-transition information on session graph. Based on BGNN, we propose a novel approach, called Session-based Recommendation with Global Information (SRGI), which infers the user preferences via fully exploring global item-transitions over all sessions from two different perspectives: (i) Fusion-based Model (SRGI-FM), which recursively incorporates the neighbor embeddings of each node on global graph into the learning process of session level item representation; and (ii) Constrained-based Model (SRGI-CM), which treats the global-level item-transition information as a constraint to ensure the learned item embeddings are consistent with the global item-transition. Extensive experiments conducted on three popular benchmark datasets demonstrate that both SRGI-FM and SRGI-CM outperform the state-of-the-art methods consistently.

cs.IR↗
arXiv2021

Exploiting Group-level Behavior Pattern forSession-based Recommendation

Session-based recommendation (SBR) is a challenging task, which aims to predict users' future interests based on anonymous behavior sequences. Existing methods leverage powerful representation learning approaches to encode sessions into a low-dimensional space. However, despite such achievements, all the existing studies focus on the instance-level session learning, while neglecting the group-level users' preference, which is significant to model the users' behavior. To this end, we propose a novel Repeat-aware Neural Mechanism for Session-based Recommendation (RNMSR). In RNMSR, we propose to learn the user preference from both instance-level and group-level, respectively: (i) instance-level, which employs GNNs on a similarity-based item-pairwise session graph to capture the users' preference in instance-level. (ii) group-level, which converts sessions into group-level behavior patterns to model the group-level users' preference. In RNMSR, we combine instance-level user preference and group-level user preference to model the repeat consumption of users, \ie whether users take repeated consumption and which items are preferred by users. Extensive experiments are conducted on three real-world datasets, \ie Diginetica, Yoochoose, and Nowplaying, demonstrating that the proposed method consistently achieves state-of-the-art performance in all the tests.

cs.IR↗
arXiv2021

Deep Cross-modal Hashing via Margin-dynamic-softmax Loss

Due to their high retrieval efficiency and low storage cost for cross-modal search task, cross-modal hashing methods have attracted considerable attention. For the supervised cross-modal hashing methods, how to make the learned hash codes preserve semantic information sufficiently contained in the label of datapoints is the key to further enhance the retrieval performance. Hence, almost all supervised cross-modal hashing methods usually depends on defining a similarity between datapoints with the label information to guide the hashing model learning fully or partly. However, the defined similarity between datapoints can only capture the label information of datapoints partially and misses abundant semantic information, then hinders the further improvement of retrieval performance. Thus, in this paper, different from previous works, we propose a novel cross-modal hashing method without defining the similarity between datapoints, called Deep Cross-modal Hashing via \textit{Margin-dynamic-softmax Loss} (DCHML). Specifically, DCHML first trains a proxy hashing network to transform each category information of a dataset into a semantic discriminative hash code, called proxy hash code. Each proxy hash code can preserve the semantic information of its corresponding category well. Next, without defining the similarity between datapoints to supervise the training process of the modality-specific hashing networks , we propose a novel \textit{margin-dynamic-softmax loss} to directly utilize the proxy hashing codes as supervised information. Finally, by minimizing the novel \textit{margin-dynamic-softmax loss}, the modality-specific hashing networks can be trained to generate hash codes which can simultaneously preserve the cross-modal similarity and abundant semantic information well.

cs.CV↗
arXiv2021

GPR: Grasp Pose Refinement Network for Cluttered Scenes

Object grasping in cluttered scenes is a widely investigated field of robot manipulation. Most of the current works focus on estimating grasp pose from point clouds based on an efficient single-shot grasp detection network. However, due to the lack of geometry awareness of the local grasping area, it may cause severe collisions and unstable grasp configurations. In this paper, we propose a two-stage grasp pose refinement network which detects grasps globally while fine-tuning low-quality grasps and filtering noisy grasps locally. Furthermore, we extend the 6-DoF grasp with an extra dimension as grasp width which is critical for collisionless grasping in cluttered scenes. It takes a single-view point cloud as input and predicts dense and precise grasp configurations. To enhance the generalization ability, we build a synthetic single-object grasp dataset including 150 commodities of various shapes, and a multi-object cluttered scene dataset including 100k point clouds with robust, dense grasp poses and mask annotations. Experiments conducted on Yumi IRB-1400 Robot demonstrate that the model trained on our dataset performs well in real environments and outperforms previous methods by a large margin.

cs.RO↗
arXiv2021

Target Guided Emotion Aware Chat Machine

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leverage target information for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

cs.CL↗
arXiv2021

A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting

Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains efficiently when building data-driven dialog models. The most recent researches on domain adaption focus on giving the model a better initialization, rather than optimizing the adaptation process. We propose an efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model to emphasize the different impacts between generated tokens with respect to the context. We first train our base dialog model and meta-teacher model adversarially in a meta-learning setting on rich-resource domains. The meta-teacher learns to quantify the importance of tokens under different contexts across different domains. During adaptation, the meta-teacher guides the dialog model to focus on important tokens in order to achieve better adaptation efficiency. We evaluate our model on two multi-domain datasets, MultiWOZ and Google Schema-Guided Dialogue, and achieve state-of-the-art performance.

cs.CL↗
arXiv2021

Knowledge Injection into Dialogue Generation via Language Models

Dialogue generation has been successfully learned from scratch by neural networks, but tends to produce the same general response, e.g., "what are you talking about?", in many conversations. To reduce this homogeneity, external knowledge such as the speaker's profile and domain knowledge is applied as an additional condition to diversify a model's output. The required knowledge to develop an effective conversation, however, is not always available, which is different from prior work's assumption that a model always has acquired sufficient knowledge before chatting. This problem can be detrimental when applying a dialogue model like this chatting online with unconstrained people and topics, because the model does not have the needed knowledge. To address this problem, we propose InjK, which is a two-stage approach to inject knowledge into a dialogue generation model. First, we train a large-scale language model and query it as textual knowledge. Second, we frame a dialogue generation model to sequentially generate textual knowledge and a corresponding response. Empirically, when a dialogue generation model can only access limited knowledge, our method outperforms prior work by producing more coherent and informative responses.

cs.CL↗
arXiv2021

Deep Kernel Supervised Hashing for Node Classification in Structural Networks

Node classification in structural networks has been proven to be useful in many real world applications. With the development of network embedding, the performance of node classification has been greatly improved. However, nearly all the existing network embedding based methods are hard to capture the actual category features of a node because of the linearly inseparable problem in low-dimensional space; meanwhile they cannot incorporate simultaneously network structure information and node label information into network embedding. To address the above problems, in this paper, we propose a novel Deep Kernel Supervised Hashing (DKSH) method to learn the hashing representations of nodes for node classification. Specifically, a deep multiple kernel learning is first proposed to map nodes into suitable Hilbert space to deal with linearly inseparable problem. Then, instead of only considering structural similarity between two nodes, a novel similarity matrix is designed to merge both network structure information and node label information. Supervised by the similarity matrix, the learned hashing representations of nodes simultaneously preserve the two kinds of information well from the learned Hilbert space. Extensive experiments show that the proposed method significantly outperforms the state-of-the-art baselines over three real world benchmark datasets.

cs.SI↗
arXiv2021

Research of Damped Newton Stochastic Gradient Descent Method for Neural Network Training

First-order methods like stochastic gradient descent(SGD) are recently the popular optimization method to train deep neural networks (DNNs), but second-order methods are scarcely used because of the overpriced computing cost in getting the high-order information. In this paper, we propose the Damped Newton Stochastic Gradient Descent(DN-SGD) method and Stochastic Gradient Descent Damped Newton(SGD-DN) method to train DNNs for regression problems with Mean Square Error(MSE) and classification problems with Cross-Entropy Loss(CEL), which is inspired by a proved fact that the hessian matrix of last layer of DNNs is always semi-definite. Different from other second-order methods to estimate the hessian matrix of all parameters, our methods just accurately compute a small part of the parameters, which greatly reduces the computational cost and makes convergence of the learning process much faster and more accurate than SGD. Several numerical experiments on real datesets are performed to verify the effectiveness of our methods for regression and classification problems.

cs.LG↗
arXiv2021

Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas

HDR reconstruction is an important task in computer vision with many industrial needs. The traditional approaches merge multiple exposure shots to generate HDRs that correspond to the physical quantity of illuminance of the scene. However, the tedious capturing process makes such multi-shot approaches inconvenient in practice. In contrast, recent single-shot methods predict a visually appealing HDR from a single LDR image through deep learning. But it is not clear whether the previously mentioned physical properties would still hold, without training the network to explicitly model them. In this paper, we introduce the physical illuminance constraints to our single-shot HDR reconstruction framework, with a focus on spherical panoramas. By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible. For evaluation, we collect a large dataset of LDR and HDR images with ground truth illuminance measures. Extensive experiments show that our HDR images not only maintain high visual quality but also top all baseline methods in illuminance prediction accuracy.

cs.CV↗