Search Results for author:
Found 52 papers, 37 papers with code
Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System
Despite their effectiveness under cold scenarios, we observe that they underperform simple traditional collaborative filtering models under warm scenarios due to the lack of collaborative knowledge.
DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
We investigate the replay buffer in rehearsal-based approaches for graph continual learning (GCL) methods.
Self-Guided Robust Graph Structure Refinement
However, we have discovered that existing GSR methods are limited by narrowassumptions, such as assuming clean node features, moderate structural attacks, and the availability of external clean graphs, resulting in the restricted applicability in real-world scenarios.
Adaptive Self-training Framework for Fine-grained Scene Graph Generation
To this end, we introduce a Self-Training framework for SGG (ST-SGG) that assigns pseudo-labels for unannotated triplets based on which the SGG models are trained.
Stoichiometry Representation Learning with Polymorphic Crystal Structures
Despite the recent success of machine learning (ML) in materials science, its success heavily relies on the structural description of crystal, which is itself computationally demanding and occasionally unattainable.
Handover Protocol Learning for LEO Satellite Networks: Access Delay and Collision Minimization
This study presents a novel deep reinforcement learning (DRL)-based handover (HO) protocol, called DHO, specifically designed to address the persistent challenge of long propagation delays in low-Earth orbit (LEO) satellite networks' HO procedures.
Interpretable Prototype-based Graph Information Bottleneck
In this work, we propose a novel framework of explainable GNNs, called interpretable Prototype-based Graph Information Bottleneck (PGIB) that incorporates prototype learning within the information bottleneck framework to provide prototypes with the key subgraph from the input graph that is important for the model prediction.
Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer
While previous works mainly focus on obtaining high-quality representations of crystalline materials for DOS prediction, we focus on predicting the DOS from the obtained representations by reflecting the nature of DOS: DOS determines the general distribution of states as a function of energy.
LLM4SGG: Large Language Model for Weakly Supervised Scene Graph Generation
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations.
Class Label-aware Graph Anomaly Detection
Unsupervised GAD methods assume the lack of anomaly labels, i. e., whether a node is anomalous or not.
MUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
Recommender systems have become indispensable in music streaming services, enhancing user experiences by personalizing playlists and facilitating the serendipitous discovery of new music.
S-Mixup: Structural Mixup for Graph Neural Networks
Existing studies for applying the mixup technique on graphs mainly focus on graph classification tasks, while the research in node classification is still under-explored.
Quantum Multi-Agent Reinforcement Learning for Autonomous Mobility Cooperation
To tackle these problems, a quantum MARL (QMARL) algorithm based on the concept of actor-critic network is proposed, which is beneficial in terms of scalability, to deal with the limitations in the noisy intermediate-scale quantum (NISQ) era.
Two Tales of Platoon Intelligence for Autonomous Mobility Control: Enabling Deep Learning Recipes
This paper presents the deep learning-based recent achievements to resolve the problem of autonomous mobility control and efficient resource management of autonomous vehicles and UAVs, i. e., (i) multi-agent reinforcement learning (MARL), and (ii) neural Myerson auction.
Unsupervised Episode Generation for Graph Meta-learning
Despite the effectiveness of graph contrastive learning (GCL) methods in the FSNC task without using the label information, they mainly learn generic node embeddings without consideration of the downstream task to be solved, which may limit its performance in the FSNC task.
Similarity Preserving Adversarial Graph Contrastive Learning
Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features.
Task Relation-aware Continual User Representation Learning
However, since learning task-specific user representations for every task is infeasible, recent studies introduce the concept of universal user representation, which is a more generalized representation of a user that is relevant to a variety of tasks.
Task-Equivariant Graph Few-shot Learning
To solve this problem, it is important for GNNs to be able to classify nodes with a limited number of labeled nodes, known as few-shot node classification.
Shift-Robust Molecular Relational Learning with Causal Substructure
To do so, we first assume a causal relationship based on the domain knowledge of molecular sciences and construct a structural causal model (SCM) that reveals the relationship between variables.
Conditional Graph Information Bottleneck for Molecular Relational Learning
Molecular relational learning, whose goal is to learn the interaction behavior between molecular pairs, got a surge of interest in molecular sciences due to its wide range of applications.
MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
The long-tailed problem is a long-standing challenge in Sequential Recommender Systems (SRS) in which the problem exists in terms of both users and items.
Predicting Density of States via Multi-modal Transformer
The density of states (DOS) is a spectral property of materials, which provides fundamental insights on various characteristics of materials.
Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems
This paper proposes a novel algorithm, named quantum multi-agent actor-critic networks (QMACN) for autonomously constructing a robust mobile access system employing multiple unmanned aerial vehicles (UAVs).
STERLING: Synergistic Representation Learning on Bipartite Graphs
Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs.
Coordinated Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Swarms in Autonomous Mobile Access Applications
This paper proposes a novel centralized training and distributed execution (CTDE)-based multi-agent deep reinforcement learning (MADRL) method for multiple unmanned aerial vehicles (UAVs) control in autonomous mobile access applications.
Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization
We formulate the unsupervised summarization based on the Markov decision process with rewards representing the summary quality.
Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network
Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image.
Heterogeneous Graph Learning for Multi-modal Medical Data Analysis
In this paper, we propose an effective graph-based framework called HetMed (Heterogeneous Graph Learning for Multi-modal Medical Data Analysis) for fusing the multi-modal medical data.
Software Simulation and Visualization of Quantum Multi-Drone Reinforcement Learning
Quantum machine learning (QML) has received a lot of attention according to its light training parameter numbers and speeds; and the advances of QML lead to active research on quantum multi-agent reinforcement learning (QMARL).
Multi-agent Reinforcement Learning
Quantum Machine Learning
+2
Multi-Agent Deep Reinforcement Learning for Efficient Passenger Delivery in Urban Air Mobility
It has been considered that urban air mobility (UAM), also known as drone-taxi or electrical vertical takeoff and landing (eVTOL), will play a key role in future transportation.
Set2Box: Similarity Preserving Representation Learning of Sets
Through extensive experiments on 8 real-world datasets, we show that, compared to baseline approaches, Set2Box+ is (a) Accurate: achieving up to 40. 8X smaller estimation error while requiring 60% fewer bits to encode sets, (b) Concise: yielding up to 96. 8X more concise representations with similar estimation error, and (c) Versatile: enabling the estimation of four set-similarity measures from a single representation of each set.
Cooperative Multi-Agent Deep Reinforcement Learning for Reliable and Energy-Efficient Mobile Access via Multi-UAV Control
The reliable mobile access services can be achieved in following two ways, i. e., i) energy-efficient UAV operation and ii) reliable wireless communication services.
Beyond Learning from Next Item: Sequential Recommendation via Personalized Interest Sustainability
We first formulate a task that requires to predict which items each user will consume in the recent period of the training time based on users' consumption history.
Ranked #1 on
Sequential Recommendation
on Amazon Cell Phones
LTE4G: Long-Tail Experts for Graph Neural Networks
After having trained an expert for each balanced subset, we adopt knowledge distillation to obtain two class-wise students, i. e., Head class student and Tail class student, each of which is responsible for classifying nodes in the head classes and tail classes, respectively.
Relational Self-Supervised Learning on Graphs
Despite their success, existing GRL methods tend to overlook an inherent distinction between images and graphs, i. e., images are assumed to be independently and identically distributed, whereas graphs exhibit relational information among data instances, i. e., nodes.
AHP: Learning to Negative Sample for Hyperedge Prediction
Since it is prohibitive to use all of them as negative examples for model training, it is inevitable to sample a very small portion of them, and to this end, heuristic sampling schemes have been employed.
GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment
Despite the success of Graph Neural Networks (GNNs) on various applications, GNNs encounter significant performance degradation when the amount of supervision signals, i. e., number of labeled nodes, is limited, which is expected as GNNs are trained solely based on the supervision obtained from the labeled nodes.
Shift-Robust Node Classification via Graph Adversarial Clustering
Then a shift-robust classifier is optimized on training graph and adversarial samples on target graph, which are generated by cluster GNN.
Augmentation-Free Self-Supervised Learning on Graphs
Inspired by the recent success of self-supervised methods applied on images, self-supervised learning on graph structured data has seen rapid growth especially centered on augmentation-based contrastive methods.
Learnable Structural Semantic Readout for Graph Classification
By the help of a global readout operation that simply aggregates all node (or node-cluster) representations, existing GNN classifiers obtain a graph-level representation of an input graph and predict its class label using the representation.
Bootstrapping User and Item Representations for One-Class Collaborative Filtering
To make the representations of positively-related users and items similar to each other while avoiding a collapsed solution, BUIR adopts two distinct encoder networks that learn from each other; the first encoder is trained to predict the output of the second encoder as its target, while the second encoder provides the consistent targets by slowly approximating the first encoder.
HDMI: High-order Deep Multiplex Infomax
To address the above-mentioned problems, we propose a novel framework, called High-order Deep Multiplex Infomax (HDMI), for learning node embedding on multiplex networks in a self-supervised way.
Interest Sustainability-Aware Recommender System
More precisely, we first predict the interest sustainability of each item, that is, how likely each item will be consumed in the future.
Unsupervised Differentiable Multi-aspect Network Embedding
To capture the multiple aspects of each node, existing studies mainly rely on offline graph clustering performed prior to the actual embedding, which results in the cluster membership of each node (i. e., node aspect distribution) fixed throughout training of the embedding model.
BHIN2vec: Balancing the Type of Relation in Heterogeneous Information Network
We view the heterogeneous network embedding as simultaneously solving multiple tasks in which each task corresponds to each relation type in a network.
Unsupervised Attributed Multiplex Network Embedding
Even for those that consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph.
Task-Guided Pair Embedding in Heterogeneous Network
In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e. g., paper-author relationship in author identification).
Collaborative Translational Metric Learning
We also conduct extensive qualitative evaluations on the translation vectors learned by our proposed method to ascertain the benefit of adopting the translation mechanism for implicit feedback-based recommendations.
Ranked #1 on
Recommendation Systems
on Declicious
Attention-based Dialog Embedding for Dialog Breakdown Detection
Dialog Breakdown Detection Challenge 3 of Dialog System Technology Challenge 6
Click-aware purchase prediction with push at the top
We begin by formulating various model assumptions, each one assuming a different order of user preferences among purchased, clicked-but-not-purchased, and non-clicked items, to study the usefulness of leveraging click records.
Review of multi-fidelity models
Multi-fidelity models provide a framework for integrating computational models of varying complexity, allowing for accurate predictions while optimizing computational resources.
Applications 65C99, 65D15, 68W25, 76-00, 74-00 A.1; G.3; I.6.5; I.2.8
Convolutional Matrix Factorization for Document Context-Aware Recommendation
However, due to the inherent limitation of the bag-of-words model, they have difficulties in effectively utilizing contextual information of the documents, which leads to shallow understanding of the documents.
