Search Results for author:
Found 44 papers, 19 papers with code
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories.
On the Learnability of Out-of-distribution Detection
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones.
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
The LTS-CG leverages agents' historical observations to calculate an agent-pair probability matrix, where a sparse graph is sampled from and used for knowledge exchange between agents, thereby simultaneously capturing agent dependencies and relation uncertainty.
Layer-diverse Negative Sampling for Graph Neural Networks
Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance.
Online Boosting Adaptive Learning under Concept Drift for Multistream Classification
Specifically, OBAL operates in a dual-phase mechanism, in the first of which we design an Adaptive COvariate Shift Adaptation (AdaCOSA) algorithm to construct an initialized ensemble model using archived data from various source streams, thus mitigating the covariate shift while learning the dynamic correlations via an adaptive re-weighting strategy.
Meta OOD Learning for Continuously Adaptive OOD Detection
To address CAOOD, we develop meta OOD learning (MOL) by designing a learning-to-adapt diagram such that a good initialized OOD detection model is learned during the training process.
Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes
However, there are more non-neighbour nodes in the whole graph, which provide diverse and useful information for the representation update.
Is Out-of-Distribution Detection Learnable?
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
Streaming PAC-Bayes Gaussian process regression with a performance guarantee for online decision making
The framework offers both a guarantee of generalized performance and good accuracy.
Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples
An interesting way to understand GCNs is to think of them as a message passing mechanism where each node updates its representation by accepting information from its neighbours (also known as positive samples).
Multi-class Classification with Fuzzy-feature Observations: Theory and Algorithms
Hence, in this paper, we propose a novel framework to address a new realistic problem called multi-class classification with imprecise observations (MCIMO), where we need to train a classifier with fuzzy-feature observations.
Bayesian Transfer Learning: An Overview of Probabilistic Graphical Models for Transfer Learning
Transfer learning where the behavior of extracting transferable knowledge from the source domain(s) and reusing this knowledge to target domain has become a research area of great interest in the field of artificial intelligence.
Deep Bayesian Estimation for Dynamic Treatment Regimes with a Long Follow-up Time
Causal effect estimation for dynamic treatment regimes (DTRs) contributes to sequential decision making.
Learning Bounds for Open-Set Learning
In this paper, we target a more challenging and realistic setting: open-set learning (OSL), where there exist test samples from the classes that are unseen during training.
Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data
In realistic scenarios with very limited numbers of data samples, however, it can be challenging to identify a kernel powerful enough to distinguish complex distributions.
Automatic Learning to Detect Concept Drift
Many methods have been proposed to detect concept drift, i. e., the change in the distribution of streaming data, due to concept drift causes a decrease in the prediction accuracy of algorithms.
Decentralized Statistical Inference with Unrolled Graph Neural Networks
In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination.
Distributed Optimization with Coupling Constraints
In this paper, we develop a novel distributed algorithm for addressing convex optimization with both nonlinear inequality and linear equality constraints, where the objective function can be a general nonsmooth convex function and all the constraints can be fully coupled.
Distributed Optimization
Optimization and Control
PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior
By leveraging experience from previous tasks, meta-learning algorithms can achieve effective fast adaptation ability when encountering new tasks.
How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?
Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy.
Interactive Steering of Hierarchical Clustering
The novelty of our approach includes 1) automatically constructing constraints for hierarchical clustering using knowledge (knowledge-driven) and intrinsic data distribution (data-driven), and 2) enabling the interactive steering of clustering through a visual interface (user-driven).
Concept Drift Detection: Dealing with MissingValues via Fuzzy Distance Estimations
Our solution comprises a novel masked distance learning (MDL) algorithm to reduce the cumulative errors caused by iteratively estimating each missing value in an observation and a fuzzy-weighted frequency (FWF) method for identifying discrepancies in the data distribution.
Learning from a Complementary-label Source Domain: Theory and Algorithms
We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA).
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA).
Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation
To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data.
Learning under Concept Drift: A Review
To help researchers identify which research topics are significant and how to apply related techniques in data analysis tasks, it is necessary that a high quality, instructive review of current research developments and trends in the concept drift field is conducted.
Diverse Instances-Weighting Ensemble based on Region Drift Disagreement for Concept Drift Adaptation
Concept drift refers to changes in the distribution of underlying data and is an inherent property of evolving data streams.
Learning Deep Kernels for Non-Parametric Two-Sample Tests
We propose a class of kernel-based two-sample tests, which aim to determine whether two sets of samples are drawn from the same distribution.
Ranked #1 on
Two-sample testing
on HIGGS Data Set
ATL: Autonomous Knowledge Transfer from Many Streaming Processes
It automatically evolves its network structure from scratch with/without the presence of ground truth to overcome independent concept drifts in the source and target domain.
Wildly Unsupervised Domain Adaptation and Its Powerful and Efficient Solution
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD---we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation
Wildly Unsupervised Domain Adaptation
Cross-domain Network Representations
By generating the random walks from a structural rich domain and transferring the knowledge on the random walks across domains, it enables a network representation for the structural scarce domain as well.
Open Set Domain Adaptation: Theoretical Bound and Algorithm
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- the basic strategy being to mitigate the effects of discrepancies between the two distributions.
Ranked #20 on
Domain Adaptation
on Office-Home
Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation
Wildly Unsupervised Domain Adaptation
A Choquet Fuzzy Integral Vertical Bagging Classifier for Mobile Telematics Data Analysis
The application of mobile telematics has been explored in many areas, such as insurance and road safety.
Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting
We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function.
Deep Surface Light Fields
A surface light field represents the radiance of rays originating from any points on the surface in any directions.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
Cooperative Hierarchical Dirichlet Processes: Superposition vs. Maximization
The cooperative hierarchical structure is a common and significant data structure observed in, or adopted by, many research areas, such as: text mining (author-paper-word) and multi-label classification (label-instance-feature).
Scalable Inference for Nested Chinese Restaurant Process Topic Models
Finally, we propose an efficient distributed implementation of PCGS through vectorization, pre-processing, and a careful design of the concurrent data structures and communication strategy.
Heterogeneous domain adaptation: An unsupervised approach
To contribute to the research in this emerging field, this paper presents: (1) an unsupervised knowledge transfer theorem that guarantees the correctness of transferring knowledge; and (2) a principal angle-based metric to measure the distance between two pairs of domains: one pair comprises the original source and target domains and the other pair comprises two homogeneous representations of two domains.
Dependent Indian Buffet Process-based Sparse Nonparametric Nonnegative Matrix Factorization
Under this same framework, two classes of correlation function are proposed (1) using Bivariate beta distribution and (2) using Copula function.
Nonparametric Relational Topic Models through Dependent Gamma Processes
Traditional Relational Topic Models provide a way to discover the hidden topics from a document network.
Infinite Author Topic Model based on Mixed Gamma-Negative Binomial Process
One branch of these works is the so-called Author Topic Model (ATM), which incorporates the authors's interests as side information into the classical topic model.
