Though many dynamic GNN models have emerged to learn from evolving graphs, the training process of these dynamic GNNs is dramatically different from traditional GNNs in that it captures both the spatial and temporal dependencies of graph updates.
After extensive experiments and analysis, we find that existing task orchestrating methods fail to fully utilize the heterogeneous resources, limited by inefficient CPU processing or GPU resource contention.
Many Graph Neural Network (GNN) training systems have emerged recently to support efficient GNN training.
This paper proposes the User Viewing Flow Modeling (SINGLE) method for the article recommendation task, which models the user constant preference and instant interest from user-clicked articles.
Our further analyses show that the visual module plugin method is tailored to enable the image understanding ability for an existing dense retrieval model.
In a comprehensive battery of tests on counterfactual medical image generation, BiomedJourney substantially outperforms prior state-of-the-art methods in instruction image editing and medical image generation such as InstructPix2Pix and RoentGen.
SHAP package is a leading implementation of Shapley values to explain neural networks implemented in TensorFlow or PyTorch but lacks cross-platform support, one-shot deployment and is highly inefficient.
This paper introduces an improved duration informed attention neural network (DurIAN-E) for expressive and high-fidelity text-to-speech (TTS) synthesis.
Noise-robust TTS models are often trained using the enhanced speech, which thus suffer from speech distortion and background noise that affect the quality of the synthesized speech.
TASTE alleviates the cold start problem by representing long-tail items using full-text modeling and bringing the benefits of pretrained language models to recommendation systems.
Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users.
1 code implementation • 7 Aug 2023 • Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, Minlie Huang, Yuxiao Dong, Jie Tang
We present AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting.
Instruction tuning has proven effective for distilling LLMs into more cost-efficient models such as Alpaca and Vicuna.
Ranked #1 on Named Entity Recognition on ACE 2005
Clinical trial matching is a key process in health delivery and discovery.
We find that while LLMs already possess decent competency in structuring biomedical text, by distillation into a task-specific student model through self-supervised learning, substantial gains can be attained over out-of-box LLMs, with additional advantages such as cost, efficiency, and white-box model access.
1 code implementation • 15 Jun 2023 • Jifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, Chunyang Li, Zheyuan Zhang, Yushi Bai, Yantao Liu, Amy Xin, Nianyi Lin, Kaifeng Yun, Linlu Gong, Jianhui Chen, Zhili Wu, Yunjia Qi, Weikai Li, Yong Guan, Kaisheng Zeng, Ji Qi, Hailong Jin, Jinxin Liu, Yu Gu, Yuan YAO, Ning Ding, Lei Hou, Zhiyuan Liu, Bin Xu, Jie Tang, Juanzi Li
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website.
Keypoint detection and matching is a fundamental task in many computer vision problems, from shape reconstruction, to structure from motion, to AR/VR applications and robotics.
SANTA proposes two pretraining methods to make language models structure-aware and learn effective representations for structured data: 1) Structured Data Alignment, which utilizes the natural alignment relations between structured data and unstructured data for structure-aware pretraining.
To further enhance the reliability of our noise decision results, ReSup uses two networks to jointly achieve noise suppression.
Recently, many efforts have been made to explore how the brain processes speech using electroencephalographic (EEG) signals, where deep learning-based approaches were shown to be applicable in this field.
However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data.
Most existing work for grounded language understanding uses LMs to directly generate plans that can be executed in the environment to achieve the desired effects.
In this survey, we situate KBQA in the broader literature of semantic parsing and give a comprehensive account of how existing KBQA approaches attempt to address the unique challenges.
These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense retrievers.
Ranked #1 on Information Retrieval on MS MARCO
A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework.
Question answering on knowledge bases (KBQA) poses a unique challenge for semantic parsing research due to two intertwined challenges: large search space and ambiguities in schema linking.
The Temporal Link Prediction task of WSDM Cup 2022 expects a single model that can work well on two kinds of temporal graphs simultaneously, which have quite different characteristics and data properties, to predict whether a link of a given type will occur between two given nodes within a given time span.
Overall, domainspecific vocabulary and pretraining facilitate more robust models for fine-tuning.
We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets.
Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way.
The zero-velocity update (ZUPT) algorithm provides valuable state information to maintain the inertial navigation system (INS) reliability when stationary conditions are satisfied.
We present a waypoint planning algorithm for an unmanned aerial vehicle (UAV) that is teamed with an unmanned ground vehicle (UGV) for the task of search and rescue in a subterranean environment.
In recent years, speech emotion recognition technology is of great significance in industrial applications such as call centers, social robots and health care.
To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64, 331 questions, GrailQA, and provide evaluation settings for all three levels of generalization.
In this paper, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models.
Ranked #2 on Participant Intervention Comparison Outcome Extraction on EBM-NLP (using extra training data)
This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders.
By using the stability theory of perturbed linear systems, we show that the control parameters can be properly designed to ensure the closed-loop and L2 string stabilities for any given positive time headway.
We present an approach to enhance wheeled planetary rover dead-reckoning localization performance by leveraging the use of zero-type constraint equations in the navigation filter.
Principal component analysis (PCA) is a fundamental dimension reduction tool in statistics and machine learning.