Search Results for author:
Found 64 papers, 26 papers with code
Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software.
OpenAgents: An Open Platform for Language Agents in the Wild
Language agents show potential in being capable of utilizing natural language for varied and intricate tasks in diverse environments, particularly when built upon large language models (LLMs).
End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based Reconciliation
Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i. e., the forecasts should satisfy the hierarchical aggregation constraints.
Lemur: Harmonizing Natural Language and Code for Language Agents
We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agents.
EasyTPP: Towards Open Benchmarking Temporal Point Processes
In this paper, we present EasyTPP, the first central repository of research assets (e. g., data, models, evaluation programs, documentations) in the area of event sequence modeling.
Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
Large language models have shown astonishing performance on a wide range of reasoning tasks.
WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine
We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain.
From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning
Empirical results on various benchmarks validate that the integration of SQL execution leads to significant improvements in zero-shot scenarios, particularly in table reasoning.
A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability
Owing to its generalization, MixDA has penetrated a variety of applications which are also completely reviewed in this work.
Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i. e., acquiring new knowledge and skills with little or even no demonstration.
A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances
The deluge of digital information in our daily life -- from user-generated content, such as microblogs and scientific papers, to online business, such as viral marketing and advertising -- offers unprecedented opportunities to explore and exploit the trajectories and structures of the evolution of information cascades.
CCGL: Contrastive Cascade Graph Learning
Second, it learns a generic model for graph cascade tasks via self-supervised contrastive pre-training using both unlabeled and labeled data.
Ranked #1 on
Information Cascade Popularity Prediction
on Weibo
Deep Active Learning: Unified and Principled Method for Query and Training
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning.
Trajectory-User Linking via Variational AutoEncoder
Trajectory-User Linking (TUL) is an essential task in Geo-tagged social media (GTSM) applications, enabling personalized Point of Interest (POI) recommendation and activity identification.
Dissecting Human and LLM Preferences
As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation.
A Heterogeneous Dynamical Graph Neural Networks Approach to Quantify Scientific Impact
Quantifying and predicting the long-term impact of scientific writings or individual scholars has important implications for many policy decisions, such as funding proposal evaluation and identifying emerging research fields.
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data
Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment.
Spatial-Temporal Contrasting for Fine-Grained Urban Flow Inference
Fine-grained urban flow inference (FUFI) problem aims to infer the fine-grained flow maps from coarse-grained ones, benefiting various smart-city applications by reducing electricity, maintenance, and operation costs.
Ranked #1 on
Fine-Grained Urban Flow Inference
on TaxiBJ-P4
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
We define two types of entropy-based metrics, i. e. (1) the discarding of pixel-wise information used in the forward propagation, and (2) the uncertainty of the input reconstruction, to measure input information contained by a specific layer from two perspectives.
Graph-Based Semi-Supervised Learning with Non-ignorable Non-response
Graph-based semi-supervised learning is a very powerful tool in classification tasks, while in most existing literature the labelled nodes are assumed to be randomly sampled.
Graph-Based Equilibrium Metrics for Dynamic Supply-Demand Systems with Applications to Ride-sourcing Platforms
How to dynamically measure the local-to-global spatio-temporal coherence between demand and supply networks is a fundamental task for ride-sourcing platforms, such as DiDi.
Optimization and Control Applications
Variance Control for Distributional Reinforcement Learning
Although distributional reinforcement learning (DRL) has been widely examined in the past few years, very few studies investigate the validity of the obtained Q-function estimator in the distributional setting.
Distributional Reinforcement Learning
reinforcement-learning
Deep Optimal Timing Strategies for Time Series
Deciding the best future execution time is a critical task in many business activities while evolving time series forecasting, and optimal timing strategy provides such a solution, which is driven by observed data.
Hessian Aware Low-Rank Weight Perturbation for Continual Learning
We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method.
On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization
We establish the convergence results of K-AVG for nonconvex objectives and explain why the K-step delay is necessary and leads to better performance than traditional parallel stochastic gradient descent which is a special case of K-AVG with $K=1$.
The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising
In addition, the bounds established for HOSVD also elaborate the one-sided sup-norm perturbation bounds for the singular subspaces of unbalanced (or fat) matrices.
Nonparametric Estimation of Low Rank Matrix Valued Function
We also propose another new estimator based on bias-reducing kernels to study the case when $A$ is not necessarily low rank and establish an upper bound on its risk measured by $L_{\infty}$-norm.
Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
A dense block was introduced to improve the performance of extractor in DRU.
Ranked #2 on
JPEG Artifact Correction
on LIVE1 (Quality 20 Color)
Color Image Compression Artifact Reduction
Image Compression Artifact Reduction
+3
ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks
This paper describes the architecture and performance of ORACLE, an approach for detecting a unique radio from a large pool of bit-similar devices (same hardware, protocol, physical address, MAC ID) using only IQ samples at the physical layer.
A Distributed Hierarchical SGD Algorithm with Sparse Global Reduction
Reducing communication in training large-scale machine learning applications on distributed platform is still a big challenge.
A Fourier Analytical Approach to Estimation of Smooth Functions in Gaussian Shift Model
Let $\mathbf{x}_j = \mathbf{\theta} + \mathbf{\epsilon}_j$, $j=1,\dots, n$ be i. i. d.
Relational State-Space Model for Stochastic Multi-Object Systems
Real-world dynamical systems often consist of multiple stochastic subsystems that interact with each other.
Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay
Graph Neural Networks (GNNs) have recently received significant research attention due to their superior performance on a variety of graph-related learning tasks.
Metric learning by Similarity Network for Deep Semi-Supervised Learning
Deep semi-supervised learning has been widely implemented in the real-world due to the rapid development of deep learning.
Discriminative Active Learning for Domain Adaptation
To this end, we introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation.
Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder
To tackle these challenges, we present a semi-supervised text classification framework that integrates multi-head attention mechanism with Semi-supervised variational inference for Operational Risk Classification (SemiORC).
Interpreting Twitter User Geolocation
Identifying user geolocation in online social networks is an essential task in many location-based applications.
Domain Generalization via Optimal Transport with Metric Similarity Learning
Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary.
Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence
We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence.
Alpha-DAG: a reinforcement learning based algorithm to learn Directed Acyclic Graphs
Directed acyclic graphs (DAGs) are widely used to model the casual relationships among random variables in many disciplines.
Non-Crossing Quantile Regression for Distributional Reinforcement Learning
Distributional reinforcement learning (DRL) estimates the distribution over future returns instead of the mean to more efficiently capture the intrinsic uncertainty of MDPs.
Embedding Symbolic Temporal Knowledge into Deep Sequential Models
However, when data is limited, simpler models such as logic/rule-based methods work surprisingly well, especially when relevant prior knowledge is applied in their construction.
Multi-task Learning by Leveraging the Semantic Information
To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions.
Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning
Although distributional reinforcement learning (DRL) has been widely examined in the past few years, there are two open questions people are still trying to address.
Directional Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
Rate-Optimal Subspace Estimation on Random Graphs
We show that the performance of estimating the connectivity matrix $M$ depends on the sparsity of the graph.
LSTOD: Latent Spatial-Temporal Origin-Destination prediction model and its applications in ride-sharing platforms
Origin-Destination (OD) flow data is an important instrument in transportation studies.
Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks
Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have achieved new state-of-the-arts on various tasks such as table question answering, table type recognition, column relation classification, table search, formula prediction, etc.
Gap Minimization for Knowledge Sharing and Transfer
Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.
Automatic Registration of Images with Inconsistent Content Through Line-Support Region Segmentation and Geometrical Outlier Removal
This new approach is designed to address the problems associated with the registration of images with affine deformations and inconsistent content, such as remote sensing images with different spectral content or noise interference, or map images with inconsistent annotations.
Evolving Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
Numerical reasoning over natural language has been a long-standing goal for the research community.
Incorporating Interactive Facts for Stock Selection via Neural Recursive ODEs
Stock selection attempts to rank a list of stocks for optimizing investment decision making, aiming at minimizing investment risks while maximizing profit returns.
Predicting Human Mobility via Self-supervised Disentanglement Learning
However, most of the existing research concentrates on fusing different semantics underlying sequential trajectories for mobility pattern learning which, in turn, yields a narrow perspective on comprehending human intrinsic motions.
Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization
When the initial policy is consistent, under some mild conditions, our method will yield a policy whose value converges to the optimal one at a faster rate than the initial policy, achieving the desired ``value enhancement" property.
SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies
Moreover, unlike most previous reconciliation methods which either rely on strong assumptions or focus on coherent constraints only, we utilize deep neural optimization networks, which not only achieve coherency without any assumptions, but also allow more flexible and realistic constraints to achieve task-based targets, e. g., lower under-estimation penalty and meaningful decision-making loss to facilitate the subsequent downstream tasks.
Urban Regional Function Guided Traffic Flow Prediction
The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest.
Multi-modal Representation Learning for Social Post Location Inference
Inferring geographic locations via social posts is essential for many practical location-based applications such as product marketing, point-of-interest recommendation, and infector tracking for COVID-19.
Continuous Invariance Learning
To address this challenge, we then propose Continuous Invariance Learning (CIL), which extracts invariant features across continuously indexed domains.
Generalizing across Temporal Domains with Koopman Operators
By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains.
Prediction of Translation Techniques for the Translation Process
Machine translation (MT) encompasses a variety of methodologies aimed at enhancing the accuracy of translations.
The Comparison of Translationese in Machine Translation and Human Transation in terms of Translation Relations
This study explores the distinctions between neural machine translation (NMT) and human translation (HT) through the lens of translation relations.
