Search Results for author:
Found 163 papers, 44 papers with code
DiDi’s Machine Translation System for WMT2020
This paper describes the DiDi AI Labs’ submission to the WMT2020 news translation shared task.
MyESL: Sparse learning in molecular evolution and phylogenetic analysis
The computational core of MyESL is written in C++, which offers model building with or without group sparsity, while the pre- and post-processing of inputs and model outputs is performed using customized functions written in Python.
ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
To address this challenge, we propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2SQL, thereby providing a more practical solution.
HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
Generating high-quality novel view renderings of 3D Gaussian Splatting (3DGS) in scenes featuring transient objects is challenging.
Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
In this paper, we analyze the distribution of attention scores for image tokens across each layer and head of the model, revealing an intriguing and common phenomenon: most hallucinations are closely linked to the pattern of attention sinks in the self-attention matrix of image tokens, where shallow layers exhibit dense attention sinks and deeper layers show sparse attention sinks.
Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
The ubiquity and value of tables as semi-structured data across various domains necessitate advanced methods for understanding their complexity and vast amounts of information.
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
This technique leverages semantic features to control the representation of LLM's intermediate hidden states, enabling the model to meet specific requirements such as increased honesty or heightened safety awareness.
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences.
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
To address these limitations, we propose a novel self-correcting adaptive planning paradigm for KG-augmented LLM named Plan-on-Graph (PoG), which first decomposes the question into several sub-objectives and then repeats the process of adaptively exploring reasoning paths, updating memory, and reflecting on the need to self-correct erroneous reasoning paths until arriving at the answer.
SciPIP: An LLM-based Scientific Paper Idea Proposer
Based on a user-provided research background, SciPIP retrieves helpful papers from a literature database while leveraging the capabilities of LLMs to generate more novel and feasible ideas.
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
(2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents.
Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding
Recent development of protein language models (pLMs) with supervised fine tuning provides a promising solution to this problem.
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
We observe performance dips in question-answering benchmarks after the removal or expansion of the shallow layers, and the degradation shrinks as the layer gets deeper, indicating that the shallow layers hold the key to knowledge injection.
SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs
Knowledge graphs (KGs) play a pivotal role in knowledge-intensive tasks across specialized domains, where the acquisition of precise and dependable knowledge is crucial.
Interpreting and Improving Large Language Models in Arithmetic Calculation
In this work, we delve into uncovering a specific mechanism by which LLMs execute calculations.
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
Recent works propose to employ supervised fine-tuning (SFT) to mitigate the sycophancy issue, while it typically leads to the degeneration of LLMs' general capability.
GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching
As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services.
ESOD: Efficient Small Object Detection on High-Resolution Images
The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs.
Enhancing LLM's Cognition via Structurization
Besides, we show the feasibility of distilling advanced LLMs' language processing abilities to a smaller yet effective StruXGPT-7B to execute structurization, addressing the practicality of our approach.
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions.
Structure-aware Domain Knowledge Injection for Large Language Models
Remarkably, our method demonstrates the potential of comparable improvement against the state-of-the-art MMedLM2 on MMedBench, while significantly reducing the training costs to 5%.
Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions
The key to OOD detection has two aspects: generalized feature representation and precise category description.
A3S: A General Active Clustering Method with Pairwise Constraints
Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying.
URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering
To address these limitations, we propose a novel Unified and Robust Representation Learning for Incomplete Multi-View Clustering (URRL-IMVC).
AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization
In this study, we introduce a new problem raised by social media and photojournalism, named Image Address Localization (IAL), which aims to predict the readable textual address where an image was taken.
PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models
Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving.
Discrete Latent Perspective Learning for Segmentation and Detection
In this paper, we address the challenge of Perspective-Invariant Learning in machine learning and computer vision, which involves enabling a network to understand images from varying perspectives to achieve consistent semantic interpretation.
CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer
Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal.
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
Large Vision Language Models (LVLMs) achieve great performance on visual-language reasoning tasks, however, the black-box nature of LVLMs hinders in-depth research on the reasoning mechanism.
RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception
We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more challenging traffic scenes.
ROPO: Robust Preference Optimization for Large Language Models
Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses.
Learning Neural Volumetric Pose Features for Camera Localization
We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses.
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV
In this paper, we address the challenge of multi-object tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left/right, and moving up/down, lead to significantly greater complexity compared to fixed-camera MOT.
MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection
By aggregating the visual word and visual sentence features, our MiM-ISTD can effectively explore both global and local information.
IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations.
INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs.
Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
Most existing OOD detection methods focused on exploring advanced training skills or training-free tricks to prevent the model from yielding overconfident confidence score for unknown samples.
Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
This bidirectional interaction narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations.
Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning
This limitation hinders the potential of language supervision emphasized in CLIP and restricts the learning of temporal features as the text encoder has demonstrated limited proficiency in motion understanding.
LLaFS: When Large Language Models Meet Few-Shot Segmentation
This paper proposes LLaFS, the first attempt to leverage large language models (LLMs) in few-shot segmentation.
Concise and Organized Perception Facilitates Reasoning in Large Language Models
Exploiting large language models (LLMs) to tackle reasoning has garnered growing attention.
Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects
An emerging research area within these services is service Route\&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker.
Uncertainty-aware Unsupervised Multi-Object Tracking
The resulting accurate pseudo-tracklets boost learning the feature consistency.
Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal
Inspired by the various successful applications of large-scale pre-trained models (e. g, CLIP), in this paper, we explore the potential benefits of them for this task through both spatial feature representation learning and semantic information embedding aspects: 1) for spatial feature representation learning, we design a Spatially-Adaptive Residual (\textbf{SAR}) Encoder to extract degraded areas adaptively.
Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark
With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field.
Ranked #1 on
Semantic Segmentation
on INRIA Aerial Image Labeling
(mIOU metric)
Self-Learning Symmetric Multi-view Probabilistic Clustering
Then, SLS-MPC proposes a novel self-learning probability function without any prior knowledge and hyper-parameters to learn each view's individual distribution.
Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems
However, building a user simulator with no reality-gap, i. e., can predict user's feedback exactly, is unrealistic because the users' reaction patterns are complex and historical logs for each user are limited, which might mislead the simulator-based recommendation policy.
Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module
The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models.
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization in a non-stationary environment.
ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization
In detail, by studying the long-tailed distribution of node degrees in the graph, we propose a novel normalization method for GNNs, which is termed ResNorm (\textbf{Res}haping the long-tailed distribution into a normal-like distribution via \textbf{norm}alization).
Stochastic Gradient Descent without Full Data Shuffle
In this paper, we first conduct a systematic empirical study on existing data shuffling strategies, which reveals that all existing strategies have room for improvement -- they all suffer in terms of I/O performance or convergence rate.
Policy Evaluation for Temporal and/or Spatial Dependent Experiments
The aim of this paper is to establish a causal link between the policies implemented by technology companies and the outcomes they yield within intricate temporal and/or spatial dependent experiments.
Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Surprisingly, we observe from experiments that the graph structure modeling in GCNs does not have a significant impact on the performance of KGC models, which is in contrast to the common belief.
Offline Model-based Adaptable Policy Learning
Current offline reinforcement learning methods commonly learn in the policy space constrained to in-support regions by the offline dataset, in order to ensure the robustness of the outcome policies.
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
Then, given any extrinsic reward, the agent computes the policy via a planning algorithm with offline data collected in the exploration phase.
A Deep Value-network Based Approach for Multi-Driver Order Dispatching
In this work, we propose a deep reinforcement learning based solution for order dispatching and we conduct large scale online A/B tests on DiDi's ride-dispatching platform to show that the proposed method achieves significant improvement on both total driver income and user experience related metrics.
Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
In this paper we propose a unified value-based dynamic learning framework (V1D3) for tackling both tasks.
Reinforcement Learning for Ridesharing: An Extended Survey
In this paper, we present a comprehensive, in-depth survey of the literature on reinforcement learning approaches to decision optimization problems in a typical ridesharing system.
Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-demand, MoD) platforms.
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
A REINFORCEMENT LEARNING FRAMEWORK FOR TIME DEPENDENT CAUSAL EFFECTS EVALUATION IN A/B TESTING
A/B testing, or online experiment is a standard business strategy to compare a new product with an old one in pharmaceutical, technological, and traditional industries.
Offline Adaptive Policy Leaning in Real-World Sequential Recommendation Systems
Instead of increasing the fidelity of models for policy learning, we handle the distortion issue via learning to adapt to diverse simulators generated by the offline dataset.
Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Inspired by the effectiveness of pseudo-labels in domain adaptation, we propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation.
Domain Adaptation with Incomplete Target Domains
In the proposed model, we design a data imputation module to fill the missing feature values based on the partial observations in the target domain, while aligning the two domains via deep adversarial adaption.
Bi-Dimensional Feature Alignment for Cross-Domain Object Detection
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community.
Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach
To address this issue, we propose a deep multi-task multi-graph learning approach, which combines two components: (1) multiple multi-graph convolutional (MGC) networks for predicting demands for different service modes, and (2) multi-task learning modules that enable knowledge sharing across multiple MGC networks.
Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction
In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.
DiDi's Machine Translation System for WMT2020
This paper describes DiDi AI Labs' submission to the WMT2020 news translation shared task.
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks.
Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution
Graph neural networks have become an important tool for modeling structured data.
A Survey on Machine Learning from Few Samples
The capability of learning and generalizing from very few samples successfully is a noticeable demarcation separating artificial intelligence and human intelligence since humans can readily establish their cognition to novelty from just a single or a handful of examples whereas machine learning algorithms typically entail hundreds or thousands of supervised samples to guarantee generalization ability.
Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning
Existing approaches for this problem are based on two-timescale or double-loop stochastic gradient algorithms, which may also require sampling large-batch data.
Predicting Individual Treatment Effects of Large-scale Team Competitions in a Ride-sharing Economy
Through interpreting the best-performing models, we discover many novel and actionable insights regarding how to optimize the design and the execution of team competitions on ride-sharing platforms.
PropagationNet: Propagate Points to Curve to Learn Structure Information
Deep learning technique has dramatically boosted the performance of face alignment algorithms.
Ranked #4 on
Face Alignment
on WFLW
Road Network Metric Learning for Estimated Time of Arrival
To address the data sparsity problem, we propose the Road Network Metric Learning framework for ETA (RNML-ETA).
Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data
In this paper, we present our proposed ensemble model with batch spectral regularization and data blending mechanisms for the Track 2 problem of the cross-domain few-shot learning (CD-FSL) challenge.
A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning
The TMHFS method extends the Meta-Confidence Transduction (MCT) and Dense Feature-Matching Networks (DFMN) method [2] by introducing a new prediction head, i. e, an instance-wise global classification network based on semantic information, after the common feature embedding network.
Fusion Recurrent Neural Network
Furthermore, in order to evaluate Fusion RNN's sequence feature extraction capability, we choose a representative data mining task for sequence data, estimated time of arrival (ETA) and present a novel model based on Fusion RNN.
FMA-ETA: Estimating Travel Time Entirely Based on FFN With Attention
Estimated time of arrival (ETA) is one of the most important services in intelligent transportation systems and becomes a challenging spatial-temporal (ST) data mining task in recent years.
Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification
In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge.
Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
In this work, we propose a matching network, called sequential sentence matching network (S2M), to use the sentence-level semantic information to address the problem.
Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
Recently, deep learning based methods have achieved promising results by adopting graph convolutional network (GCN) to extract the spatial correlations and recurrent neural network (RNN) to capture the temporal dependencies.
Hierarchical Adaptive Contextual Bandits for Resource Constraint based Recommendation
In this paper, we propose a hierarchical adaptive contextual bandit method (HATCH) to conduct the policy learning of contextual bandits with a budget constraint.
Predicting Origin-Destination Flow via Multi-Perspective Graph Convolutional Network
Predicting Origin-Destination (OD) flow is a crucial problem for intelligent transportation.
Adaptive Object Detection with Dual Multi-Label Prediction
In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task.
Mutual Learning Network for Multi-Source Domain Adaptation
However, in practice the labeled data can come from multiple source domains with different distributions.
Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
At last, we proposed a differentiable auto data augmentation method to further improve estimation accuracy.
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
In particular, we prove that the proposed algorithm achieves $\widetilde{\mathcal{O}}(L|\mathcal{S}|\sqrt{|\mathcal{A}|T})$ upper bounds of both the regret and the constraint violation, where $L$ is the length of each episode.
Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework
A/B testing, or online experiment is a standard business strategy to compare a new product with an old one in pharmaceutical, technological, and traditional industries.
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Generative adversarial networks (GANs) are a hot research topic recently.
An Attention-based Graph Neural Network for Heterogeneous Structural Learning
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations.
Deep Reinforcement Learning for Multi-Driver Vehicle Dispatching and Repositioning Problem
Order dispatching and driver repositioning (also known as fleet management) in the face of spatially and temporally varying supply and demand are central to a ride-sharing platform marketplace.
Building Effective Large-Scale Traffic State Prediction System: Traffic4cast Challenge Solution
How to build an effective large-scale traffic state prediction system is a challenging but highly valuable problem.
Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network
To overcome this challenge, we propose the Spatio-Temporal Encoder-Decoder Residual Multi-Graph Convolutional network (ST-ED-RMGC), a novel deep learning model for predicting ride-sourcing demand of various OD pairs.
Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching
Improving the efficiency of dispatching orders to vehicles is a research hotspot in online ride-hailing systems.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Multi-grained Attention Networks for Single Image Super-Resolution
In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.
PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
The key problem in graph node embedding lies in how to define the dependence to neighbors.
CGT: Clustered Graph Transformer for Urban Spatio-temporal Prediction
Deep learning based approaches have been widely used in various urban spatio-temporal forecasting problems, but most of them fail to account for the unsmoothness issue of urban data in their architecture design, which significantly deteriorates their prediction performance.
AHINE: Adaptive Heterogeneous Information Network Embedding
In this paper, we propose two novel algorithms, GHINE (General Heterogeneous Information Network Embedding) and AHINE (Adaptive Heterogeneous Information Network Embedding), to compute distributed representations for elements in heterogeneous networks.
Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting
This task is challenging due to the complicated spatiotemporal dependencies among regions.
Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation
DEMER also derives a recommendation policy with a significantly improved performance in the test phase of the real application.
Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle
In this paper, we define and investigate a general reward trans-formation problem (namely, reward advancement): Recovering the range of additional reward functions that transform the agent's policy from original policy to a predefined target policy under MCE principle.
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose an innovative additional purification step for further weight reduction without accuracy loss; and (iii) develop effective heuristic search method enhanced by experience-based guided search, replacing the prior deep reinforcement learning technique which has underlying incompatibility with the target pruning problem.
CoRide: Joint Order Dispatching and Fleet Management for Multi-Scale Ride-Hailing Platforms
How to optimally dispatch orders to vehicles and how to trade off between immediate and future returns are fundamental questions for a typical ride-hailing platform.
Multiagent Systems
Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting
To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks.
Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning
Vacant taxi drivers' passenger seeking process in a road network generates additional vehicle miles traveled, adding congestion and pollution into the road network and the environment.
Object Detection in 20 Years: A Survey
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years.
D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios
Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models.
POI Semantic Model with a Deep Convolutional Structure
An accurate similarity calculation is challenging since the mismatch between a query and a retrieval text may exist in the case of a mistyped query or an alias inquiry.
Which Factorization Machine Modeling is Better: A Theoretical Answer with Optimal Guarantee
This bound is sub-optimal comparing to the information theoretical lower bound $\mathcal{O}(kd)$.
Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining
In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so that fewer cars are required to fulfill the given amount of trip demand.
P^2IR: Universal Deep Node Representation via Partial Permutation Invariant Set Functions
Our method can 1) learn an arbitrary form of the representation function from the neighborhood, without losing any potential dependence structures, 2) automatically decide the significance of neighbors at different distances, and 3) be applicable to both homogeneous and heterogeneous graph embedding, which may contain multiple types of nodes.
GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning
Graph embedding is a central problem in social network analysis and many other applications, aiming to learn the vector representation for each node.
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations.
A Unified Neural Network Approach for Estimating Travel Time and Distance for a Taxi Trip
In building intelligent transportation systems such as taxi or rideshare services, accurate prediction of travel time and distance is crucial for customer experience and resource management.
Identifying Genetic Risk Factors via Sparse Group Lasso with Group Graph Structure
As a regression model, it is competitive to the state-of-the-arts sparse models; as a variable selection method, SGLGG is promising for identifying Alzheimer's disease-related risk SNPs.
Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images
Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks.
Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis
However, the development of a robust and reliable deep learning model for computer-aided diagnosis is still highly challenging due to the combination of the high heterogeneity in the medical images and the relative lack of training samples.
Efficient Approximate Solutions to Mutual Information Based Global Feature Selection
Estimating the MI for a subset of features is often intractable.
Coupled Support Vector Machines for Supervised Domain Adaptation
Popular domain adaptation (DA) techniques learn a classifier for the target domain by sampling relevant data points from the source and combining it with the target data.
Large-scale Feature Selection of Risk Genetic Factors for Alzheimer's Disease via Distributed Group Lasso Regression
Then we select the relevant group features by performing the group Lasso feature selection process in a sequence of parameters.
Nonconvex One-bit Single-label Multi-label Learning
We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels.
The Second Order Linear Model
We show that the conventional gradient descent heuristic is biased by the skewness of the distribution therefore is no longer the best practice of learning the SLM.
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing
We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees.
Large-scale Collaborative Imaging Genetics Studies of Risk Genetic Factors for Alzheimer's Disease Across Multiple Institutions
To the best of our knowledge, this is the first successful run of the computationally intensive model selection procedure to learn a consistent model across different institutions without compromising their privacy while ranking the SNPs that may collectively affect AD.
Seeing the Forest from the Trees in Two Looks: Matrix Sketching by Cascaded Bilateral Sampling
Given a matrix A of size m by n, state-of-the-art randomized algorithms take O(m * n) time and space to obtain its low-rank decomposition.
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs.
Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection
By a novel hierarchical projection algorithm, MLFre is able to test the nodes independently from any of their ancestor nodes.
HONOR: Hybrid Optimization for NOn-convex Regularized problems
(2) We establish a rigorous convergence analysis for HONOR, which shows that convergence is guaranteed even for non-convex problems, while it is typically challenging to analyze the convergence for non-convex problems.
Safe Screening for Multi-Task Feature Learning with Multiple Data Matrices
One of the appealing features of DPC is that: it is safe in the sense that the detected inactive features are guaranteed to have zero coefficients in the solution vectors across all tasks.
Two-Layer Feature Reduction for Sparse-Group Lasso via Decomposition of Convex Sets
Sparse-Group Lasso (SGL) has been shown to be a powerful regression technique for simultaneously discovering group and within-group sparse patterns by using a combination of the $\ell_1$ and $\ell_2$ norms.
Persistent Homology in Sparse Regression and Its Application to Brain Morphometry
Sparse systems are usually parameterized by a tuning parameter that determines the sparsity of the system.
Stochastic Coordinate Coding and Its Application for Drosophila Gene Expression Pattern Annotation
The effectiveness of gene expression pattern annotation relies on the quality of feature representation.
Linear Convergence of Variance-Reduced Stochastic Gradient without Strong Convexity
Under the strongly convex condition, these variance-reduced stochastic gradient algorithms achieve a linear convergence rate.
Geodesic Distance Function Learning via Heat Flow on Vector Fields
Based on our theoretical analysis, we propose to first learn the gradient field of the distance function and then learn the distance function itself.
Orthogonal Rank-One Matrix Pursuit for Low Rank Matrix Completion
Numerical results show that our proposed algorithm is more efficient than competing algorithms while achieving similar or better prediction performance.
Generalization Bounds for Representative Domain Adaptation
Finally, we analyze the asymptotic convergence and the rate of convergence of the learning process for representative domain adaptation.
Forward-Backward Greedy Algorithms for General Convex Smooth Functions over A Cardinality Constraint
Our new bounds are consistent with the bounds of a special case (least squares) and fills a previously existing theoretical gap for general convex smooth functions; 3) We show that the restricted strong convexity condition is satisfied if the number of independent samples is more than $\bar{k}\log d$ where $\bar{k}$ is the sparsity number and $d$ is the dimension of the variable; 4) We apply FoBa-gdt (with the conditional random field objective) to the sensor selection problem for human indoor activity recognition and our results show that FoBa-gdt outperforms other methods (including the ones based on forward greedy selection and L1-regularization).
Scaling SVM and Least Absolute Deviations via Exact Data Reduction
Some appealing features of our screening method are: (1) DVI is safe in the sense that the vectors discarded by DVI are guaranteed to be non-support vectors; (2) the data set needs to be scanned only once to run the screening, whose computational cost is negligible compared to that of solving the SVM problem; (3) DVI is independent of the solvers and can be integrated with any existing efficient solvers.
Safe Screening With Variational Inequalities and Its Application to LASSO
Safe screening is gaining increasing attention since 1) solving sparse learning formulations usually has a high computational cost especially when the number of features is large and 2) one needs to try several regularization parameters to select a suitable model.
Efficient Mixed-Norm Regularization: Algorithms and Safe Screening Methods
One key building block of the proposed algorithm is the l1q-regularized Euclidean projection (EP_1q).
A Safe Screening Rule for Sparse Logistic Regression
The l1-regularized logistic regression (or sparse logistic regression) is a widely used method for simultaneous classification and feature selection.
Dictionary LASSO: Guaranteed Sparse Recovery under Linear Transformation
Specifically, we show 1) in the noiseless case, if the condition number of $D$ is bounded and the measurement number $n\geq \Omega(s\log(p))$ where $s$ is the sparsity number, then the true solution can be recovered with high probability; and 2) in the noisy case, if the condition number of $D$ is bounded and the measurement increases faster than $s\log(p)$, that is, $s\log(p)=o(n)$, the estimate error converges to zero with probability 1 when $p$ and $s$ go to infinity.
Generalization Bounds for Domain Adaptation
Afterwards, we analyze the asymptotic convergence and the rate of convergence of the learning process for such kind of domain adaptation.
A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems
A commonly used approach is the Multi-Stage (MS) convex relaxation (or DC programming), which relaxes the original non-convex problem to a sequence of convex problems.
Multi-task Vector Field Learning
MTVFL has the following key properties: (1) the vector fields we learned are close to the gradient fields of the prediction functions; (2) within each task, the vector field is required to be as parallel as possible which is expected to span a low dimensional subspace; (3) the vector fields from all tasks share a low dimensional subspace.
Multi-Stage Multi-Task Feature Learning
In this paper, we propose a non-convex formulation for multi-task sparse feature learning based on a novel regularizer.
Lasso Screening Rules via Dual Polytope Projection
To improve the efficiency of solving large-scale Lasso problems, El Ghaoui and his colleagues have proposed the SAFE rules which are able to quickly identify the inactive predictors, i. e., predictors that have $0$ components in the solution vector.
Fused Multiple Graphical Lasso
We expect the two brain networks for NC and MCI to share common structures but not to be identical to each other; similarly for the two brain networks for MCI and AD.
Efficient Methods for Overlapping Group Lasso
There have been several recent attempts to study a more general formulation, where groups of features are given, potentially with overlaps between the groups.
Identifying Alzheimer's Disease-Related Brain Regions from Multi-Modality Neuroimaging Data using Sparse Composite Linear Discrimination Analysis
This is especially true for early AD, at which stage the disease-related regions are most likely to be weak-effect regions that are difficult to be detected from a single modality alone.