Search Results for author:
Found 47 papers, 15 papers with code
GMAN: A Graph Multi-Attention Network for Traffic Prediction
Between the encoder and the decoder, a transform attention layer is applied to convert the encoded traffic features to generate the sequence representations of future time steps as the input of the decoder.
Ranked #2 on
Image Dehazing
on KITTI
Federated Learning with Fair Averaging
Fairness has emerged as a critical problem in federated learning (FL).
A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning
In the last few years, the interest in knowledge bases has grown exponentially in both the research community and the industry due to their essential role in AI applications.
Contrastive Trajectory Similarity Learning with Dual-Feature Attention
Trajectory similarity measures act as query predicates in trajectory databases, making them the key player in determining the query results.
WGCN: Graph Convolutional Networks with Weighted Structural Features
Based on nodes' geometrical relationships in the latent space, WGCN differentiates latent, in-, and out-neighbors with an attention-based geometrical aggregation.
FedGS: Federated Graph-based Sampling with Arbitrary Client Availability
Second, constrained by the far-distance in data distribution of the sampled clients, we further minimize the variance of the numbers of times that the clients are sampled, to mitigate long-term bias.
PeerSum: A Peer Review Dataset for Abstractive Multi-document Summarization
We present PeerSum, a new MDS dataset using peer reviews of scientific publications.
INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
It aims to infer knowledge for (the things at) unobserved locations using the data from (the things at) observed locations during a given time period of interest.
Fast, Accurate and Interpretable Time Series Classification Through Randomization
r-STSF is highly efficient, achieves state-of-the-art classification accuracy and enables interpretability.
A Graph and Attentive Multi-Path Convolutional Network for Traffic Prediction
To model the temporal factors, we use a multi-path convolutional neural network (CNN) to learn the joint impact of different combinations of past traffic conditions on the future traffic conditions.
Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization
A series of datasets and models have been proposed for summaries generated for well-formatted documents such as news articles.
Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization
We propose HGSUM, an MDS model that extends an encoder-decoder architecture, to incorporate a heterogeneous graph to represent different semantic units (e. g., words and sentences) of the documents.
AutoAlign: Fully Automatic and Effective Knowledge Graph Alignment enabled by Large Language Models
In this paper, we propose the first fully automatic alignment method named AutoAlign, which does not require any manually crafted seed alignments.
Fake News Detection Through Temporally Evolving User Interactions
We join this model with a neural Hawkes process model to exploit the distinctive self-exciting patterns of true news and fake news on social media.
Spatial-temporal Forecasting for Regions without Observations
Our key insight is to learn from the locations that resemble those in the region of interest, and we propose a selective masking strategy to enable the learning.
A Jointly Learned Context-Aware Place of Interest Embedding for Trip Recommendations
We propose two trip recommendation algorithms based on our context-aware POI embedding.
Scalable Bottom-up Subspace Clustering using FP-Trees for High Dimensional Data
Subspace clustering aims to find groups of similar objects (clusters) that exist in lower dimensional subspaces from a high dimensional dataset.
PubSE: A Hierarchical Model for Publication Extraction from Academic Homepages
Publication information in a researcher{'}s academic homepage provides insights about the researcher{'}s expertise, research interests, and collaboration networks.
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data
However, this representation is not in a natural language form, which is difficult for humans to understand.
Ranked #12 on
Data-to-Text Generation
on WebNLG
KDGAN: Knowledge Distillation with Generative Adversarial Networks
An alternative method is to adversarially train the classifier against a discriminator in a two-player game akin to generative adversarial networks (GAN), which can ensure the classifier to learn the true data distribution at the equilibrium of this game.
A Joint Model for Multimodal Document Quality Assessment
The quality of a document is affected by various factors, including grammaticality, readability, stylistics, and expertise depth, making the task of document quality assessment a complex one.
CBHE: Corner-based Building Height Estimation for Complex Street Scene Images
CBHE first obtains building corner and roofline candidates in street scene images based on building footprints from 2D maps and the camera parameters.
Neural Relation Extraction for Knowledge Base Enrichment
This way, NED errors may cause extraction errors that affect the overall precision and recall. To address this problem, we propose an end-to-end relation extraction model for KB enrichment based on a neural encoder-decoder model.
Generative Image Inpainting with Submanifold Alignment
Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal.
CARL: Aggregated Search with Context-Aware Module Embedding Learning
To model and utilize the context information for aggregated search, we propose a model with context attention and representation learning (CARL).
Boosted GAN with Semantically Interpretable Information for Image Inpainting
Forexample, given a male image with image region of one eye missing, current models may restore it with a female eye.
Modelling Uncertainty in Collaborative Document Quality Assessment
In the context of document quality assessment, previous work has mainly focused on predicting the quality of a document relative to a putative gold standard, without paying attention to the subjectivity of this task.
MALA: Cross-Domain Dialogue Generation with Action Learning
These two components, however, have a discrepancy in their objectives, i. e., task completion and language quality.
SANST: A Self-Attentive Network for Next Point-of-Interest Recommendation
To address this limitation, in this paper, we propose a model named SANST that incorporates spatio-temporal patterns of user check-ins into self-attentive networks.
Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation
This approach requires complete state-action annotations of human-to-human dialogues (i. e., expert demonstrations), which is labor intensive.
Short-Term and Long-Term Context Aggregation Network for Video Inpainting
Video inpainting aims to restore missing regions of a video and has many applications such as video editing and object removal.
Generalizable and Explainable Dialogue Generation via Explicit Action Learning
To alleviate the need of action annotations, latent action learning is introduced to map each utterance to a latent representation.
Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random
In recommender systems, usually the ratings of a user to most items are missing and a critical problem is that the missing ratings are often missing not at random (MNAR) in reality.
HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks
Experimental results show that compared with the state-of-the-art models, which imitate hexagonal processing but using rectangle-shaped filters, HexCNN reduces the training time by up to 42. 2%.
Evaluating Document Coherence Modelling
While pretrained language models ("LM") have driven impressive gains over morpho-syntactic and semantic tasks, their ability to model discourse and pragmatic phenomena is less clear.
Grouped-Attention for Content-Selection and Content-Plan Generation
A key component of the GSC-attention is grouped-attention, which is token-level attention constrained within each input attribute that enables our proposed model captures both local and global context.
Findings on Conversation Disentanglement
Conversation disentanglement, the task to identify separate threads in conversations, is an important pre-processing step in multi-party conversational NLP applications such as conversational question answering and conversation summarization.
Conversational Question Answering
Conversation Disentanglement
+2
TransAlign: Fully Automatic and Effective Entity Alignment for Knowledge Graphs
The task of entity alignment between knowledge graphs (KGs) aims to identify every pair of entities from two different KGs that represent the same entity.
WISK: A Workload-aware Learned Index for Spatial Keyword Queries
In this paper, we propose WISK, a learned index for spatial keyword queries, which self-adapts for optimizing querying costs given a query workload.
CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network
However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data.
Fake News Detection Through Graph-based Neural Networks: A Survey
In recent years, graph-based methods have yielded strong results, as they can closely model the social context and propagation process of online news.
Urban Region Representation Learning with Attentive Fusion
Our model is powered by a dual-feature attentive fusion module named DAFusion, which fuses embeddings from different region features to learn higher-order correlations between the regions as well as between the different types of region features.
