However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.
Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields.
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.
The spurious correlations over hybrid distribution deviation degrade the performance of previous GNN methods and show large instability among different datasets.
Large language models (LLMs) have achieved great success in general domains of natural language processing.
Achieving coordination between humans and artificial intelligence in scenarios involving previously unencountered humans remains a substantial obstacle within Zero-Shot Human-AI Coordination, which aims to develop AI agents capable of efficiently working alongside previously unknown human teammates.
The results demonstrate that our system has broad prospects and can assist researchers in expediting the process of discovering new ideas.
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
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.
In this work, we propose Covidia, COVID-19 interdisciplinary academic knowledge graph to bridge the gap between knowledge of COVID-19 on different domains.
We further employ the asymmetric focusing mechanism to decouple the gradient contribution from the negative and positive samples.
Graph representation learning has been widely studied and demonstrated effectiveness in various graph tasks.
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.
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks.
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
The design of our framework consists of two aspects: a prompt planner and a knowledge adapter.
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.
This is achieved by aligning the hierarchy of the rooted-tree of a central node with the ordered neurons in its node representation.
Ranked #2 on Node Classification on Cornell
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.
Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery.
Understanding the origin and influence of the publication's idea is critical to conducting scientific research.
As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.
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.
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.
Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype.
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
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
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.
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)
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.
An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph.
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.
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.
Analyzing the groups in the network based on same attributes, functions or connections between nodes is a way to understand network information.
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.
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 #171 on Image Classification on CIFAR-10
For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.
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.
Thus, in this paper, we exploit adaptive dispatching intervals to boost the platform's profit under a guarantee of the maximum passenger waiting time.
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.
In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning.
Ranked #1 on Community Detection on DBLP
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.
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.