Search Results for author:
Found 172 papers, 96 papers with code
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
The advancement of Multimodal Large Language Models (MLLMs) has enabled significant progress in multimodal understanding, expanding their capacity to analyze video content.
Crystal Structure Generation Based On Material Properties
The discovery of new materials is very important to the field of materials science.
Polymetis:Large Language Modeling for Multiple Material Domains
As the application of large language models in various fields continues to expand, materials science also ushers in opportunities for AI-driven innovation.
Material Property Prediction with Element Attribute Knowledge Graphs and Multimodal Representation Learning
Machine learning has become a crucial tool for predicting the properties of crystalline materials.
A dynamic auction for multilateral collaboration
We study the problem of multilateral collaboration among agents with transferable utilities.
Multi-Channel Hypergraph Contrastive Learning for Matrix Completion
The (rating) matrix completion is essentially a rating prediction process, which is also a significant problem in recommender systems.
Scaling Concept With Text-Guided Diffusion Models
Through an empirical study, we identify a trend where concepts can be decomposed in text-guided diffusion models.
Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation
Secondly, we introduce a cross-modal semantic enhancement approach.
LightRAG: Simple and Fast Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.
Model-Based Reward Shaping for Adversarial Inverse Reinforcement Learning in Stochastic Environments
In this paper, we aim to tackle the limitation of the Adversarial Inverse Reinforcement Learning (AIRL) method in stochastic environments where theoretical results cannot hold and performance is degraded.
Simulation Results of Center-Manifold-Based Identification of Polynomial Nonlinear Systems with Uncontrollable Linearization
Recently, a system identification method based on center manifold is proposed to identify polynomial nonlinear systems with uncontrollable linearization.
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training.
Reactive Multi-Robot Navigation in Outdoor Environments Through Uncertainty-Aware Active Learning of Human Preference Landscape
The prediction accuracy and adaptation speed results show the effectiveness of PLBA in preference learning and MRS behavior adaption.
GP-GPT: Large Language Model for Gene-Phenotype Mapping
To address these challenges, we present GP-GPT, the first specialized large language model for genetic-phenotype knowledge representation and genomics relation analysis.
EasyST: A Simple Framework for Spatio-Temporal Prediction
Spatio-temporal prediction is a crucial research area in data-driven urban computing, with implications for transportation, public safety, and environmental monitoring.
AnyGraph: Graph Foundation Model in the Wild
Furthermore, we have validated the model's fast adaptation ability and scaling law emergence, showcasing its versatility.
OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction
Accurate traffic forecasting is crucial for effective urban planning and transportation management, enabling efficient resource allocation and enhanced travel experiences.
EasyRec: Simple yet Effective Language Models for Recommendation
Deep neural networks have become a powerful technique for learning representations from user-item interaction data in collaborative filtering (CF) for recommender systems.
Modeling and Driving Human Body Soundfields through Acoustic Primitives
While rendering and animation of photorealistic 3D human body models have matured and reached an impressive quality over the past years, modeling the spatial audio associated with such full body models has been largely ignored so far.
Understanding is Compression
The better a large model understands the data, the better LMCompress compresses.
Ranking LLMs by compression
We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression.
DiffMM: Multi-Modal Diffusion Model for Recommendation
To address this limitation, recent research has introduced self-supervised learning techniques to enhance recommender systems.
Exploiting Uncommon Text-Encoded Structures for Automated Jailbreaks in LLMs
Existing jailbreak attacks, including character-level and context-level attacks, mainly focus on the prompt of the plain text without specifically exploring the significant influence of its structure.
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
The Value Iteration Network (VIN) is an end-to-end differentiable architecture that performs value iteration on a latent MDP for planning in reinforcement learning (RL).
XRec: Large Language Models for Explainable Recommendation
We introduce a model-agnostic framework called XRec, which enables LLMs to provide comprehensive explanations for user behaviors in recommender systems.
RecDiff: Diffusion Model for Social Recommendation
This means that users connected by social ties tend to have similar tastes in user-item activities, such as rating and purchasing.
SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation
Firstly, existing sequential models primarily focus on long-term modeling of individual interaction sequences, overlooking the valuable short-term collaborative relationships among the behaviors of different users.
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
Additionally, we incorporate a distribution mapping mechanism to align the data distributions of pre-training and downstream data, facilitating effective knowledge transfer in spatio-temporal forecasting.
Variational Delayed Policy Optimization
In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL).
Learning Geospatial Region Embedding with Heterogeneous Graph
In this paper, we present GeoHG, an effective heterogeneous graph structure for learning comprehensive region embeddings for various downstream tasks.
A Survey of Large Language Models for Graphs
This survey aims to serve as a valuable resource for researchers and practitioners eager to leverage large language models in graph learning, and to inspire continued progress in this dynamic field.
Revisiting a Pain in the Neck: Semantic Phrase Processing Benchmark for Language Models
We introduce LexBench, a comprehensive evaluation suite enabled to test language models (LMs) on ten semantic phrase processing tasks.
Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning
Multi-view learning has become a popular research topic in recent years, but research on the cross-application of classic multi-label classification and multi-view learning is still in its early stages.
A Comprehensive Survey on Self-Supervised Learning for Recommendation
Recommender systems play a crucial role in tackling the challenge of information overload by delivering personalized recommendations based on individual user preferences.
Graph Augmentation for Recommendation
To address these challenges, we propose a principled framework called GraphAug.
Dual-Channel Multiplex Graph Neural Networks for Recommendation
Nevertheless, these approaches still grapple with two significant shortcomings: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations in the behavior patterns on the target relation in recommender system scenarios.
OpenGraph: Towards Open Graph Foundation Models
Secondly, we introduce a unified graph tokenizer that enables the model to generalize effectively to diverse graph data, even when encountering unseen properties during training.
Mode Consensus Algorithms With Finite Convergence Time
This paper studies the distributed mode consensus problem in a multi-agent system, in which the agents each possess a certain attribute and they aim to agree upon the mode (the most frequent attribute owned by the agents) via distributed computation.
PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning
Additionally, to adjust the impact of inaccuracies in multimedia data, a disentangled multi-modal list-wise distillation is developed with modality-aware re-weighting mechanism.
FedUV: Uniformity and Variance for Heterogeneous Federated Learning
Based on this finding, we introduce two regularization terms for local training to continuously emulate IID settings: (1) variance in the dimension-wise probability distribution of the classifier and (2) hyperspherical uniformity of representations of the encoder.
UrbanGPT: Spatio-Temporal Large Language Models
These findings highlight the potential of building large language models for spatio-temporal learning, particularly in zero-shot scenarios where labeled data is scarce.
HiGPT: Heterogeneous Graph Language Model
However, existing frameworks for heterogeneous graph learning have limitations in generalizing across diverse heterogeneous graph datasets.
GraphEdit: Large Language Models for Graph Structure Learning
Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data by generating novel graph structures.
Convergence Analysis of Split Federated Learning on Heterogeneous Data
We further extend the analysis to non-convex objectives and the scenario where some clients may be unavailable during training.
MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipeline
However, the iterative reading and updating process of the memory module in MTGNNs to obtain up-to-date information needs to follow the temporal dependencies.
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments.
Video Understanding with Large Language Models: A Survey
With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly.
DiffKG: Knowledge Graph Diffusion Model for Recommendation
To bridge this research gap, we propose a novel knowledge graph diffusion model for recommendation, referred to as DiffKG.
Combined Invariant Subspace \& Frequency-Domain Subspace Method for Identification of Discrete-Time MIMO Linear Systems
Recently, a novel system identification method based on invariant subspace theory is introduced, aiming to address the identification problem of continuous-time (CT) linear time-invariant (LTI) systems by combining time-domain and frequency-domain methods.
GraphPro: Graph Pre-training and Prompt Learning for Recommendation
The temporal prompt mechanism encodes time information on user-item interaction, allowing the model to naturally capture temporal context, while the graph-structural prompt learning mechanism enables the transfer of pre-trained knowledge to adapt to behavior dynamics without the need for continuous incremental training.
Empowering Autonomous Driving with Large Language Models: A Safety Perspective
Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly in out-of-distribution and uncertain data.
Self-Supervised Deconfounding Against Spatio-Temporal Shifts: Theory and Modeling
It first encodes traffic data into two disentangled representations for associating invariant and variant ST contexts.
Bridging Dimensions: Confident Reachability for High-Dimensional Controllers
Autonomous systems are increasingly implemented using end-to-end learning-based controllers.
GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks
This strategy guides the mask autoencoder in learning robust spatio-temporal representations and facilitates the modeling of different relationships, ranging from intra-cluster to inter-cluster, in an easy-to-hard training manner.
State-Wise Safe Reinforcement Learning With Pixel Observations
In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations.
LLMRec: Large Language Models with Graph Augmentation for Recommendation
By employing these strategies, we address the challenges posed by sparse implicit feedback and low-quality side information in recommenders.
Multilateral matching with scale economies
This paper studies multilateral matching in which any set of agents can negotiate contracts.
Spatio-Temporal Meta Contrastive Learning
Although recent STGNN models with contrastive learning aim to address these challenges, most of them use pre-defined augmentation strategies that heavily depend on manual design and cannot be customized for different Spatio-Temporal Graph (STG) scenarios.
Explainable Spatio-Temporal Graph Neural Networks
Furthermore, we propose a structure distillation approach based on the Graph Information Bottleneck (GIB) principle with an explainable objective, which is instantiated by the STG encoder and decoder.
Representation Learning with Large Language Models for Recommendation
RLMRec incorporates auxiliary textual signals, develops a user/item profiling paradigm empowered by LLMs, and aligns the semantic space of LLMs with the representation space of collaborative relational signals through a cross-view alignment framework.
GraphGPT: Graph Instruction Tuning for Large Language Models
The open-sourced model implementation of our GraphGPT is available at https://github. com/HKUDS/GraphGPT.
Incentive Mechanism Design for Distributed Ensemble Learning
To this end, we propose an alternating algorithm that iteratively updates each learner's training data size and reward.
Price of Stability in Quality-Aware Federated Learning
The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising.
CCAE: A Corpus of Chinese-based Asian Englishes
The ontology of data would make the corpus a helpful resource with enormous research potential for Asian Englishes (especially for Chinese Englishes for which there has not been a publicly accessible corpus yet so far) and an ideal source for variety-specific language modeling and downstream tasks, thus setting the stage for NLP-based World Englishes studies.
A Prototype-Based Neural Network for Image Anomaly Detection and Localization
This paper proposes ProtoAD, a prototype-based neural network for image anomaly detection and localization.
Localized and Balanced Efficient Incomplete Multi-view Clustering
Specifically, LBIMVC develops a new graph regularized incomplete multi-matrix-factorization model to obtain the unique clustering result by learning a consensus probability representation, where each element of the consensus representation can directly reflect the probability of the corresponding sample to the class.
Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields
Room impulse response (RIR), which measures the sound propagation within an environment, is critical for synthesizing high-fidelity audio for a given environment.
Kinematics-aware Trajectory Generation and Prediction with Latent Stochastic Differential Modeling
However, it remains a challenging problem for these methods to ensure that the generated/predicted trajectories are physically realistic.
Concave many-to-one matching
We propose a notion of concavity in two-sided many-to-one matching, which is an analogue to the balancedness condition in cooperative games.
Multi-Relational Contrastive Learning for Recommendation
Personalized recommender systems play a crucial role in capturing users' evolving preferences over time to provide accurate and effective recommendations on various online platforms.
When MiniBatch SGD Meets SplitFed Learning:Convergence Analysis and Performance Evaluation
SplitFed learning (SFL) is a recent distributed approach that alleviates computation workload at the client device by splitting the model at a cut layer into two parts, where clients only need to train part of the model.
How Expressive are Graph Neural Networks in Recommendation?
Most existing works adopt the graph isomorphism test as the metric of expressiveness, but this graph-level task may not effectively assess a model's ability in recommendation, where the objective is to distinguish nodes of different closeness.
SSLRec: A Self-Supervised Learning Framework for Recommendation
Our SSLRec platform covers a comprehensive set of state-of-the-art SSL-enhanced recommendation models across different scenarios, enabling researchers to evaluate these cutting-edge models and drive further innovation in the field.
High-Quality Visually-Guided Sound Separation from Diverse Categories
We compare DAVIS to existing state-of-the-art discriminative audio-visual separation methods on the AVE and MUSIC datasets, and results show that DAVIS outperforms other methods in separation quality, demonstrating the advantages of our framework for tackling the audio-visual source separation task.
Feature Importance Measurement based on Decision Tree Sampling
Random forest is effective for prediction tasks but the randomness of tree generation hinders interpretability in feature importance analysis.
Knowledge Graph Self-Supervised Rationalization for Recommendation
By masking important knowledge with high rational scores, KGRec is trained to rebuild and highlight useful knowledge connections that serve as rationales.
FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation
Specifically, we leverage the contrastive loss to learn representations of both the foreground and background regions in the images.
Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
In addition, we introduce a cross-view contrastive learning paradigm to model the inter-dependencies across view-specific region representations and preserve underlying relation heterogeneity.
SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detection
We then design a novel patch-wise residual module in the anomaly learning head to extract and assess the fine-grained anomaly features from each sample, facilitating the learning of discriminative representations of anomaly instances.
LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
To mitigate these limitations, we introduce the LargeST benchmark dataset.
Ranked #1 on
Traffic Prediction
on LargeST
Graph Transformer for Recommendation
This paper presents a novel approach to representation learning in recommender systems by integrating generative self-supervised learning with graph transformer architecture.
Denoised Self-Augmented Learning for Social Recommendation
Social recommendation is gaining increasing attention in various online applications, including e-commerce and online streaming, where social information is leveraged to improve user-item interaction modeling.
Adaptive Graph Contrastive Learning for Recommendation
These approaches conduct self-supervised learning through creating contrastive views, but they depend on the tedious trial-and-error selection of augmentation methods.
Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors
Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions.
Cost-efficient Crowdsourcing for Span-based Sequence Labeling: Worker Selection and Data Augmentation
This paper introduces a novel crowdsourcing worker selection algorithm, enhancing annotation quality and reducing costs.
Graph Masked Autoencoder for Sequential Recommendation
While some powerful neural network architectures (e. g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from poor representation capability in label scarcity scenarios.
Automated Spatio-Temporal Graph Contrastive Learning
In this paper, we tackle the above challenges by exploring the Automated Spatio-Temporal graph contrastive learning paradigm (AutoST) over the heterogeneous region graph generated from multi-view data sources.
Disentangled Contrastive Collaborative Filtering
Recent studies show that graph neural networks (GNNs) are prevalent to model high-order relationships for collaborative filtering (CF).
Information Recovery-Driven Deep Incomplete Multiview Clustering Network
Concretely, a two-stage autoencoder network with the self-attention structure is built to synchronously extract high-level semantic representations of multiple views and recover the missing data.
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions.
Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys
Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits.
Egocentric Audio-Visual Object Localization
In this paper, we explore the challenging egocentric audio-visual object localization task and observe that 1) egomotion commonly exists in first-person recordings, even within a short duration; 2) The out-of-view sound components can be created while wearers shift their attention.
Debiased Contrastive Learning for Sequential Recommendation
This solution is designed to tackle the popularity bias issue in recommendation systems.
Graph-less Collaborative Filtering
Motivated by these limitations, we propose a simple and effective collaborative filtering model (SimRec) that marries the power of knowledge distillation and contrastive learning.
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification
To deal with the double incomplete multi-view multi-label classification problem, we propose a deep instance-level contrastive network, namely DICNet.
Automated Self-Supervised Learning for Recommendation
This does not generalize across different datasets and downstream recommendation tasks, which is difficult to be adaptive for data augmentation and robust to noise perturbation.
Disentangled Graph Social Recommendation
In this work, we design a Disentangled Graph Neural Network (DGNN) with the integration of latent memory units, which empowers DGNN to maintain factorized representations for heterogeneous types of user and item connections.
Heterogeneous Graph Contrastive Learning for Recommendation
In light of this, we propose a Heterogeneous Graph Contrastive Learning (HGCL), which is able to incorporate heterogeneous relational semantics into the user-item interaction modeling with contrastive learning-enhanced knowledge transfer across different views.
Multi-Modal Self-Supervised Learning for Recommendation
The online emergence of multi-modal sharing platforms (eg, TikTok, Youtube) is powering personalized recommender systems to incorporate various modalities (eg, visual, textual and acoustic) into the latent user representations.
Multi-Behavior Graph Neural Networks for Recommender System
Recent years have witnessed the emerging success of many deep learning-based recommendation models for augmenting collaborative filtering architectures with various neural network architectures, such as multi-layer perceptron and autoencoder.
LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
In this paper, we propose a simple yet effective graph contrastive learning paradigm LightGCL that mitigates these issues impairing the generality and robustness of CL-based recommenders.
Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking diferent trajectories to users with the exploration of complex mobility patterns.
Do We Really Need Graph Neural Networks for Traffic Forecasting?
Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting.
CIGAR: Cross-Modality Graph Reasoning for Domain Adaptive Object Detection
To overcome these problems, we propose a cross-modality graph reasoning adaptation (CIGAR) method to take advantage of both visual and linguistic knowledge.
Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering
Graph-based multi-view clustering has attracted extensive attention because of the powerful clustering-structure representation ability and noise robustness.
Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction
ii) These models fail to capture the temporal heterogeneity induced by time-varying traffic patterns, as they typically model temporal correlations with a shared parameterized space for all time periods.
Ranked #1 on
Traffic Prediction
on BJTaxi
Quantifying the Impact of Label Noise on Federated Learning
Federated Learning (FL) is a distributed machine learning paradigm where clients collaboratively train a model using their local (human-generated) datasets.
Firm-worker hypergraphs
A firm-worker hypergraph consists of edges in which each edge joins a firm and its possible employees.
Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning
Detecting anomalous trajectories has become an important task in many location-based applications.
Diving into Unified Data-Model Sparsity for Class-Imbalanced Graph Representation Learning
The effectiveness is further guaranteed and proved by the gradients' distance between the subset and the full set; (ii) empirically, we discover that during the learning process of a GNN, some samples in the training dataset are informative for providing gradients to update model parameters.
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions.
A Tool for Neural Network Global Robustness Certification and Training
Moreover, GROCET provides differentiable global robustness, which is leveraged in the training of globally robust neural networks.
Multiplex Heterogeneous Graph Convolutional Network
Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous network data, ranging from link prediction to node classification.
Localized Sparse Incomplete Multi-view Clustering
Moreover, a novel local graph embedding term is introduced to learn the structured consensus representation.
Self-Supervised Hypergraph Transformer for Recommender Systems
With the distilled global context, a cross-view generative self-supervised learning component is proposed for data augmentation over the user-item interaction graph, so as to enhance the robustness of recommender systems.
Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
Further ablation studies validate the effectiveness of our model design and benefits of the new MBHT framework.
Cross-Silo Federated Learning: Challenges and Opportunities
Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private.
Multi-Behavior Sequential Recommendation with Temporal Graph Transformer
The new TGT method endows the sequential recommendation architecture to distill dedicated knowledge for type-specific behavior relational context and the implicit behavior dependencies.
RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation
We then propose RecipeRec, a novel heterogeneous graph learning model for recipe recommendation.
Two-sided matching with firms' complementary preferences
This paper studies two-sided many-to-one matching in which firms have complementary preferences.
Mutual Distillation Learning Network for Trajectory-User Linking
In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL.
Knowledge Graph Contrastive Learning for Recommendation
However, the success of such methods relies on the high quality knowledge graphs, and may not learn quality representations with two challenges: i) The long-tail distribution of entities results in sparse supervision signals for KG-enhanced item representation; ii) Real-world knowledge graphs are often noisy and contain topic-irrelevant connections between items and entities.
Hypergraph Contrastive Collaborative Filtering
Additionally, our HCCF model effectively integrates the hypergraph structure encoding with self-supervised learning to reinforce the representation quality of recommender systems, based on the hypergraph-enhanced self-discrimination.
Scalable Motif Counting for Large-scale Temporal Graphs
We first categorize the temporal motifs based on their distinct properties, and then design customized algorithms that offer efficient strategies to exactly count the motif instances of each category.
Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction
Crime has become a major concern in many cities, which calls for the rising demand for timely predicting citywide crime occurrence.
MetaSets: Meta-Learning on Point Sets for Generalizable Representations
It is a challenging problem due to the substantial geometry shift from simulated to real data, such that most existing 3D models underperform due to overfitting the complete geometries in the source domain.
Atomic Filter: a Weak Form of Shift Operator for Graph Signals
In order to establish the theory of filtering, windowed Fourier transform and wavelet transform in the setting of graph signals, we need to extend the shift operation of classical signals to graph signals.
Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding
The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations.
Contrastive Meta Learning with Behavior Multiplicity for Recommendation
In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users.
Joint Differentiable Optimization and Verification for Certified Reinforcement Learning
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e. g., safety, stability) under the learned controller.
Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems
As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, auto-encoder and graph neural networks.
Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning
Crime prediction is crucial for public safety and resource optimization, yet is very challenging due to two aspects: i) the dynamics of criminal patterns across time and space, crime events are distributed unevenly on both spatial and temporal domains; ii) time-evolving dependencies between different types of crimes (e. g., Theft, Robbery, Assault, Damage) which reveal fine-grained semantics of crimes.
Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling
Due to the overlook of user's multi-behavioral patterns over different items, existing recommendation methods are insufficient to capture heterogeneous collaborative signals from user multi-behavior data.
Decision Making for Connected Automated Vehicles at Urban Intersections Considering Social and Individual Benefits
To address the coordination issue of connected automated vehicles (CAVs) at urban scenarios, a game-theoretic decision-making framework is proposed that can advance social benefits, including the traffic system efficiency and safety, as well as the benefits of individual users.
Driving Conflict Resolution of Autonomous Vehicles at Unsignalized Intersections: A Differential Game Approach
To realize human-like driving and personalized decision-making, driving aggressiveness is first defined for AVs.
Federated Natural Language Generation for Personalized Dialogue System
FedNLG first pre-trains parameters of standard neural conversational model over a large dialogue corpus, and then fine-tune the model parameters and persona embeddings on specific datasets, in a federated manner.
Social Recommendation with Self-Supervised Metagraph Informax Network
To model relation heterogeneity, we design a metapath-guided heterogeneous graph neural network to aggregate feature embeddings from different types of meta-relations across users and items, em-powering SMIN to maintain dedicated representations for multi-faceted user- and item-wise dependencies.
Graph Meta Network for Multi-Behavior Recommendation
Modern recommender systems often embed users and items into low-dimensional latent representations, based on their observed interactions.
Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks
Social recommendation which aims to leverage social connections among users to enhance the recommendation performance.
Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network
The overlook of multiplex behavior relations can hardly recognize the multi-modal contextual signals across different types of interactions, which limit the feasibility of current recommendation methods.
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment.
Knowledge-aware Coupled Graph Neural Network for Social Recommendation
While many recent efforts show the effectiveness of neural network-based social recommender systems, several important challenges have not been well addressed yet: (i) The majority of models only consider users' social connections, while ignoring the inter-dependent knowledge across items; (ii) Most of existing solutions are designed for singular type of user-item interactions, making them infeasible to capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques.
Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation
The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space.
Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation
In particular: i) complex inter-dependencies across different types of user behaviors; ii) the incorporation of knowledge-aware item relations into the multi-behavior recommendation framework; iii) dynamic characteristics of multi-typed user-item interactions.
Recent Advances in Heterogeneous Relation Learning for Recommendation
Recommender systems have played a critical role in many web applications to meet user's personalized interests and alleviate the information overload.
Unidirectional substitutes and complements
Under the framework of matching with continuous monetary transfers and quasi-linear utilities, we show that substitutes and complements are bidirectional for a pair of workers.
When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?
In view of this, one may ask: can we leverage the additional signals from contrastive learning to alleviate data scarcity, so as to benefit STG forecasting?