Search Results for author:
Found 56 papers, 27 papers with code
RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction
However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.
Characterizing the Influence of Topology on Graph Learning Tasks
Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations.
Temporal Generalization Estimation in Evolving Graphs
In synthetic random graphs, we further refine the former lower bound to show the inevitable distortion over time and empirically observe that Smart achieves good estimation performance.
PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search
Multiple object tracking is a critical task in autonomous driving.
Is Reference Necessary in the Evaluation of NLG Systems? When and Where?
The majority of automatic metrics for evaluating NLG systems are reference-based.
Entity Alignment with Unlabeled Dangling Cases
We investigate the entity alignment problem with unlabeled dangling cases, meaning that there are entities in the source or target graph having no counterparts in the other, and those entities remain unlabeled.
AceMap: Knowledge Discovery through Academic Graph
The exponential growth of scientific literature requires effective management and extraction of valuable insights.
Graph Parsing Networks
GPN benefits from the discrete assignments generated by the graph parsing algorithm, allowing good memory efficiency while preserving node information intact.
G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection
To address this issue, we propose the Generalizable loss (G-loss), which is an OoD-aware objective, preventing NAS from over-fitting by using gradient descent to optimize parameters not only on a subset of easy-to-learn features but also the remaining predictive features for generalization, and the overall framework is named G-NAS.
Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models
However, such methods can not defend against adaptive attacks, in which an attacker takes a countermove against a known defence strategy.
GeoGalactica: A Scientific Large Language Model in Geoscience
To our best knowledge, it is the largest language model for the geoscience domain.
Domain Invariant Learning for Gaussian Processes and Bayesian Exploration
We further demonstrate the effectiveness of the DIL-GP Bayesian optimization method on a PID parameters tuning experiment for a quadrotor.
Towards Controlled Table-to-Text Generation with Scientific Reasoning
The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information.
Human-Readable Fingerprint for Large Language Models
However, identifying the original base model of an LLM is challenging due to potential parameter alterations.
Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus
Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields.
Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation
To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning.
Graph Out-of-Distribution Generalization with Controllable Data Augmentation
The spurious correlations over hybrid distribution deviation degrade the performance of previous GNN methods and show large instability among different datasets.
K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization
Large language models (LLMs) have achieved great success in general domains of natural language processing.
Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination
In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy.
Exploring and Verbalizing Academic Ideas by Concept Co-occurrence
The results demonstrate that our system has broad prospects and can assist researchers in expediting the process of discovering new ideas.
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator
Many researchers have focused on designing new forms of self-attention or introducing new parameters to overcome this limitation, however a large portion of them prohibits the model to inherit weights from large pretrained models.
Ranked #1 on
Open-Domain Question Answering
on ELI5
Prediction with Incomplete Data under Agnostic Mask Distribution Shift
We focus on the case where the underlying joint distribution of complete features and label is invariant, but the missing pattern, i. e., mask distribution may shift agnostically between training and testing.
Covidia: COVID-19 Interdisciplinary Academic Knowledge Graph
In this work, we propose Covidia, COVID-19 interdisciplinary academic knowledge graph to bridge the gap between knowledge of COVID-19 on different domains.
Asymmetric Polynomial Loss For Multi-Label Classification
We further employ the asymmetric focusing mechanism to decouple the gradient contribution from the negative and positive samples.
FMGNN: Fused Manifold Graph Neural Network
Graph representation learning has been widely studied and demonstrated effectiveness in various graph tasks.
PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model
In the research of end-to-end dialogue systems, using real-world knowledge to generate natural, fluent, and human-like utterances with correct answers is crucial.
Adapting Knowledge for Few-shot Table-to-Text Generation
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks.
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset
In this work, we first collect a large-scale institution name normalization dataset LoT-insts1, which contains over 25k classes that exhibit a naturally long-tailed distribution.
Ranked #1 on
Long-tail Learning
on Lot-insts
Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization
The design of our framework consists of two aspects: a prompt planner and a knowledge adapter.
Cooperative Open-ended Learning Framework for Zero-shot Coordination
However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility.
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
This is achieved by aligning the hierarchy of the rooted-tree of a central node with the ordered neurons in its node representation.
Ranked #4 on
Node Classification
on Cornell
Syntax-guided Localized Self-attention by Constituency Syntactic Distance
Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data.
KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction
Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery.
IdeaReader: A Machine Reading System for Understanding the Idea Flow of Scientific Publications
Understanding the origin and influence of the publication's idea is critical to conducting scientific research.
INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion
As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.
Disentangled Graph Contrastive Learning for Review-based Recommendation
In review-based recommendation methods, review data is considered as auxiliary information that can improve the quality of learned user/item or interaction representations for the user rating prediction task.
Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
To address this challenge, cross-city knowledge transfer has shown its promise, where the model learned from data-sufficient cities is leveraged to benefit the learning process of data-scarce cities.
Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation
Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype.
RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL
Our model can incorporate almost all types of existing relations in the literature, and in addition, we propose introducing co-reference relations for the multi-turn scenario.
Ranked #1 on
Dialogue State Tracking
on CoSQL
Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition
In particular, audio and visual front-ends are trained on large-scale unimodal datasets, then we integrate components of both front-ends into a larger multimodal framework which learns to recognize parallel audio-visual data into characters through a combination of CTC and seq2seq decoding.
Ranked #2 on
Automatic Speech Recognition (ASR)
on LRS2
Audio-Visual Speech Recognition
Automatic Speech Recognition (ASR)
+7
DeepShovel: An Online Collaborative Platform for Data Extraction in Geoscience Literature with AI Assistance
Geoscientists, as well as researchers in many fields, need to read a huge amount of literature to locate, extract, and aggregate relevant results and data to enable future research or to build a scientific database, but there is no existing system to support this use case well.
Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud
Experimental results show that our system not only adapts well to, but also draws on the varying contexts, delivering a practical and efficient solution to edge-cloud model training.
Ranked #2 on
Recommendation Systems
on MovieLens 1M
(Precision metric)
DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning
In addition, with such modularization, the training algorithm of DeCOM separates the original constrained optimization into an unconstrained optimization on reward and a constraints satisfaction problem on costs.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Networked Time Series Prediction with Incomplete Data via Generative Adversarial Network
An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph.
Privacy Threats Analysis to Secure Federated Learning
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.
Improved Matrix Gaussian Mechanism for Differential Privacy
The wide deployment of machine learning in recent years gives rise to a great demand for large-scale and high-dimensional data, for which the privacy raises serious concern.
Overlapping Community Detection in Temporal Text Networks
Analyzing the groups in the network based on same attributes, functions or connections between nodes is a way to understand network information.
Certified Distributional Robustness via Smoothed Classifiers
We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric.
Context-aware deep model compression for edge cloud computing
While deep neural networks (DNNs) have led to a paradigm shift, its exorbitant computational requirement has always been a roadblock in its deployment to the edge, such as wearable devices and smartphones.
Ranked #169 on
Image Classification
on CIFAR-10
Certified Distributional Robustness on Smoothed Classifiers
For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.
High-Order Relation Construction and Mining for Graph Matching
Iterated line graphs are introduced for the first time to describe such high-order information, based on which we present a new graph matching method, called High-order Graph Matching Network (HGMN), to learn not only the local structural correspondence, but also the hyperedge relations across graphs.
Spatio-Temporal Hierarchical Adaptive Dispatching for Ridesharing Systems
Thus, in this paper, we exploit adaptive dispatching intervals to boost the platform's profit under a guarantee of the maximum passenger waiting time.
On Geometric Structure of Activation Spaces in Neural Networks
Based on this new algorithm, four common geometric properties shared by the activation spaces are concluded, which gives a rather clear description of the activation spaces.
CommunityGAN: Community Detection with Generative Adversarial Nets
In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning.
Ranked #1 on
Clique Prediction
on arXiv-GrQc 3-clique
AceKG: A Large-scale Knowledge Graph for Academic Data Mining
Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine processing.
Text Network Exploration via Heterogeneous Web of Topics
A text network refers to a data type that each vertex is associated with a text document and the relationship between documents is represented by edges.
