Search Results for author:
Found 95 papers, 54 papers with code
Twist Decoding: Diverse Generators Guide Each Other
Natural language generation technology has recently seen remarkable progress with large-scale training, and many natural language applications are now built upon a wide range of generation models.
XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction
To date, work in this area has mostly focused on English as there is a scarcity of labeled data for other languages.
PyGOD: A Python Library for Graph Outlier Detection
PyGOD is an open-source Python library for detecting outliers on graph data.
Deep Reinforcement Learning Guided Graph Neural Networks for Brain Network Analysis
Modern neuroimaging techniques, such as diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI), enable us to model the human brain as a brain network or connectome.
Curvature Graph Generative Adversarial Networks
In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named \textbf{\modelname}, which is the first GAN-based graph representation method in the Riemannian geometric manifold.
Towards Unsupervised Deep Graph Structure Learning
To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning.
Sequential Recommendation via Stochastic Self-Attention
We further argue that BPR loss has no constraint on positive and sampled negative items, which misleads the optimization.
Multimodal Entity Tagging with Multimodal Knowledge Base
We also develop a dataset for the problem using an existing MKB.
Graph Structure Learning with Variational Information Bottleneck
Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications.
A Self-supervised Mixed-curvature Graph Neural Network
Instead of working on one single constant-curvature space, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces and design hierarchical attention mechanisms for learning and fusing the representations across these component spaces.
POLLA: Enhancing the Local Structure Awareness in Long Sequence Spatial-temporal Modeling
Extensive experiments are conducted on five large-scale datasets, which demonstrate that our method achieves state-of-the-art performance and validates the effectiveness brought by local structure information.
Pre-training Recommender Systems via Reinforced Attentive Multi-relational Graph Neural Network
In this paper, we propose a novel Reinforced Attentive Multi-relational Graph Neural Network (RAM-GNN) to the pre-train user and item embeddings on the user and item graph prior to the recommendation step.
Structure-Preserving Graph Kernel for Brain Network Classification
This paper presents a novel graph-based kernel learning approach for connectome analysis.
Federated Social Recommendation with Graph Neural Network
However, they all require centralized storage of the social links and item interactions of users, which leads to privacy concerns.
Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
To overcome the aforementioned problems, in light of the recent advancements in graph contrastive learning, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme.
ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network
Hyperbolic Graph Neural Networks(HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning.
3D Object Detection Combining Semantic and Geometric Features from Point Clouds
The SGNet proposed in this paper has achieved state-of-the-art results for 3D object detection in the KITTI dataset, especially in the detection of small-size objects such as cyclists.
ABC: Attention with Bounded-memory Control
One way to improve the efficiency is to bound the memory size.
TravelBERT: Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation
To obtain the aforementioned multi-format text, we construct a corpus in the tourism domain and conduct experiments on 5 tourism NLP datasets.
Event Extraction by Associating Event Types and Argument Roles
It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles.
Transferring Knowledge Distillation for Multilingual Social Event Detection
Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce.
Multiplex Graph Networks for Multimodal Brain Network Analysis
In this paper, we propose MGNet, a simple and effective multiplex graph convolutional network (GCN) model for multimodal brain network analysis.
Tailor: Generating and Perturbing Text with Semantic Controls
We craft a set of operations to modify the control codes, which in turn steer generation towards targeted attributes.
A Compact Survey on Event Extraction: Approaches and Applications
Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey.
Spatiotemporal convolutional network for time-series prediction and causal inference
Making predictions in a robust way is not easy for nonlinear systems.
Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations
Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually.
Attend and Select: A Segment Attention based Selection Mechanism for Microblog Hashtag Generation
The code and datasets are available at \url{https://github. com/OpenSUM/HashtagGen}.
Automated Timeline Length Selection for Flexible Timeline Summarization
This paper presents a better TLS approach for automatically and dynamically determining the TLS timeline length.
Noised Consistency Training for Text Summarization
In this paper, we argue that this limitation can be overcome by a semi-supervised approach: consistency training which is to leverage large amounts of unlabeled data to improve the performance of supervised learning over a small corpus.
A Robust and Generalized Framework for Adversarial Graph Embedding
With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high-quality graph embedding vectors various types of graphs.
Differentially Private Federated Knowledge Graphs Embedding
However, for multiple cross-domain knowledge graphs, state-of-the-art embedding models cannot make full use of the data from different knowledge domains while preserving the privacy of exchanged data.
Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks
Based on them, we design MinGE to directly calculate the ideal node embedding dimension for any graph.
Federated Multi-View Learning for Private Medical Data Integration and Analysis
This paper aims to provide a generic Federated Multi-View Learning (FedMV) framework for multi-view data leakage prevention, which is based on different types of local data availability and enables to accommodate two types of problems: Vertical Federated Multi-View Learning (V-FedMV) and Horizontal Federated Multi-View Learning (H-FedMV).
Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
Furthermore, they cannot fully capture the content-based correlations between nodes, as they either do not use the self-attention mechanism or only use it to consider the immediate neighbors of each node, ignoring the higher-order neighbors.
Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
To avoid the embedding over-assimilation among different types of nodes, we employ a label-aware neural similarity measure to ascertain the most similar neighbors based on node attributes.
Ranked #2 on
Node Classification
on Amazon-Fraud
HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization
The second one encourages the structure encoder to learn better representations with desired characteristics for all labels which can better handle label imbalance in hierarchical text classification.
Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions.
Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks
Third, we propose a streaming social event detection and evolution discovery framework for HINs based on meta-path similarity search, historical information about meta-paths, and heterogeneous DBSCAN clustering method.
Finetuning Pretrained Transformers into RNNs
Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune.
Ranked #1 on
Machine Translation
on WMT2017 Chinese-English
KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph
Entity synonyms discovery is crucial for entity-leveraging applications.
Random Feature Attention
RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism.
Ranked #22 on
Machine Translation
on IWSLT2014 German-English
FedMood: Federated Learning on Mobile Health Data for Mood Detection
Depression is one of the most common mental illness problems, and the symptoms shown by patients are not consistent, making it difficult to diagnose in the process of clinical practice and pathological research.
Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs
The complexity and streaming nature of social messages make it appealing to address social event detection in an incremental learning setting, where acquiring, preserving, and extending knowledge are major concerns.
SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism
Graph representation learning has attracted increasing research attention.
Heterogeneous Similarity Graph Neural Network on Electronic Health Records
EHRs contain multiple entities and relations and can be viewed as a heterogeneous graph.
Infusing Finetuning with Semantic Dependencies
For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia).
Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation
Review rating prediction of text reviews is a rapidly growing technology with a wide range of applications in natural language processing.
Learning from Context or Names? An Empirical Study on Neural Relation Extraction
We find that (i) while context is the main source to support the predictions, RE models also heavily rely on the information from entity mentions, most of which is type information, and (ii) existing datasets may leak shallow heuristics via entity mentions and thus contribute to the high performance on RE benchmarks.
Ranked #17 on
Relation Extraction
on TACRED
Kalman Filtering Attention for User Behavior Modeling in CTR Prediction
First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors.
KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning
To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output.
Contextualized Perturbation for Textual Adversarial Attack
Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness.
Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networks
Although these attributes may change, an author's co-authors and research topics do not change frequently with time, which means that papers within a period have similar text and relation information in the academic network.
Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
Finally, the selected neighbors across different relations are aggregated together.
Ranked #4 on
Node Classification
on Amazon-Fraud
Lifelong Property Price Prediction: A Case Study for the Toronto Real Estate Market
As a departure from prior work, Luce organizes the house data in a heterogeneous information network (HIN) where graph nodes are house entities and attributes that are important for house price valuation.
Adversarial Directed Graph Embedding
To capture the directed edges between nodes, existing methods mostly learn two embedding vectors for each node, source vector and target vector.
A Survey on Text Classification: From Shallow to Deep Learning
The last decade has seen a surge of research in this area due to the unprecedented success of deep learning.
A Mixture of h - 1 Heads is Better than h Heads
Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks.
Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
To address this issue, we leverage both content information and context information to learn the representation of entities via graph convolution network.
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation
We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation.
Category-Specific CNN for Visual-aware CTR Prediction at JD.com
Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR.
Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College
Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups.
Multi-step-ahead Prediction from Short-term Data by Delay-embedding-based Forecast Machine
Making accurate multi-step-ahead prediction for a complex system is a challenge for many practical applications, especially when only short-term time-series data are available.
A Mixture of $h-1$ Heads is Better than $h$ Heads
Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks.
Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection
In this paper, we introduce these inconsistencies and design a new GNN framework, $\mathsf{GraphConsis}$, to tackle the inconsistency problem: (1) for the context inconsistency, we propose to combine the context embeddings with node features, (2) for the feature inconsistency, we design a consistency score to filter the inconsistent neighbors and generate corresponding sampling probability, and (3) for the relation inconsistency, we learn a relation attention weights associated with the sampled nodes.
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
Relational facts are an important component of human knowledge, which are hidden in vast amounts of text.
Face Beautification: Beyond Makeup Transfer
Inspired by the latest advances in style-based synthesis and face beauty prediction, we propose a novel framework of face beautification.
Digital Twin: Acquiring High-Fidelity 3D Avatar from a Single Image
We present an approach to generate high fidelity 3D face avatar with a high-resolution UV texture map from a single image.
RWNE: A Scalable Random-Walk-Based Network Embedding Framework with Personalized Higher-Order Proximity Preserved
However, despite the success of current random-walk-based methods, most of them are usually not expressive enough to preserve the personalized higher-order proximity and lack a straightforward objective to theoretically articulate what and how network proximity is preserved.
HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding
Heterogeneous information network (HIN) embedding has gained increasing interests recently.
RNN Architecture Learning with Sparse Regularization
Our method also highlights the interpretable properties of rational RNNs.
PaLM: A Hybrid Parser and Language Model
We present PaLM, a hybrid parser and neural language model.
Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification
In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification.
Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks
In this paper, we design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network (HIN) integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model.
Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling
Most existing methods focus on learning the structural representations of vertices in a static network, but cannot guarantee an accurate and efficient embedding in a dynamic network scenario.
Text Generation with Exemplar-based Adaptive Decoding
We propose a novel conditioned text generation model.
Understanding Beauty via Deep Facial Features
The concept of beauty has been debated by philosophers and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability.
Graph Convolutional Neural Networks via Motif-based Attention
Different from previous convolutional neural networks on graphs, we first design a motif-matching guided subgraph normalization method to capture neighborhood information.
Modeling relation paths for knowledge base completion via joint adversarial training
By treating relations and multi-hop paths as two different input sources, we use a feature extractor, which is shared by two downstream components (i. e. relation classifier and source discriminator), to capture shared/similar information between them.
Rational Recurrences
We characterize this connection formally, defining rational recurrences to be recurrent hidden state update functions that can be written as the Forward calculation of a finite set of WFSAs.
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention
It has been applied to numerous domains, such as data augmentation, domain adaptation, and unsupervised training.
Backpropagating through Structured Argmax using a SPIGOT
We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e. g., parsing) in intermediate layers.
Learning Joint Semantic Parsers from Disjoint Data
We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap.
"You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates
We first examine the effect of wording and propose a binary classification framework that controls for both the speaker and the debate situation.
Improving Orbit Prediction Accuracy through Supervised Machine Learning
Due to the lack of information such as the space environment condition and resident space objects' (RSOs') body characteristics, current orbit predictions that are solely grounded on physics-based models may fail to achieve required accuracy for collision avoidance and have led to satellite collisions already.
Semi-supervised Structured Prediction with Neural CRF Autoencoder
In this paper we propose an end-to-end neural CRF autoencoder (NCRF-AE) model for semi-supervised learning of sequential structured prediction problems.
Asynchronous Distributed Variational Gaussian Processes for Regression
Gaussian processes (GPs) are powerful non-parametric function estimators.
Deep Multitask Learning for Semantic Dependency Parsing
We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms.
A Convolutional Attention Network for Extreme Summarization of Source Code
Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension.
A Comparative Study on Regularization Strategies for Embedding-based Neural Networks
This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP.
Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path
Relation classification is an important research arena in the field of natural language processing (NLP).
Ranked #4 on
Relation Classification
on SemEval 2010 Task 8
Discriminative Neural Sentence Modeling by Tree-Based Convolution
This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling.
Ranked #6 on
Text Classification
on TREC-6
Building Program Vector Representations for Deep Learning
In this pioneering paper, we propose the "coding criterion" to build program vector representations, which are the premise of deep learning for program analysis.
EigenGP: Gaussian Process Models with Adaptive Eigenfunctions
In this paper, we propose a new Bayesian approach, EigenGP, that learns both basis dictionary elements--eigenfunctions of a GP prior--and prior precisions in a sparse finite model.
