Search Results for author:
Found 116 papers, 61 papers with code
A Survey of Scaling in Large Language Model Reasoning
The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration.
Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models
Recent approaches leverage Graph Neural Networks (GNNs) to generate KG-based input embedding prefixes as soft prompts for LLMs but fail to account for question relevance, resulting in noisy prompts.
Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
In this paper, we propose the ReKnoS framework, which aims to Reason over Knowledge Graphs with Super-Relations.
Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems
Conversational recommender systems (CRS) aim to provide personalized recommendations via interactive dialogues with users.
Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion
In this paper, we introduce rotation symmetry, a novel form of parameter space symmetry for transformers that generalizes permutation symmetry by rotating parameter matrices in self-attention layers.
Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating
Extensive experiments demonstrate the effectiveness of LOKA in LLM knowledge updating tasks.
Harnessing Large Language Models for Disaster Management: A Survey
Large language models (LLMs) have revolutionized scientific research with their exceptional capabilities and transformed various fields.
Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization
These methods often employ a two-step strategy that first creates augmented environments and subsequently identifies invariant subgraphs to improve generalizability.
KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
Large Language Models (LLMs) have shown impressive performance in various tasks, including knowledge graph completion (KGC).
Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning
In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes.
BrainMAP: Learning Multiple Activation Pathways in Brain Networks
As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways.
ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data
However, in real-world applications, most nodes may not possess any available temporal data during training.
Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
To demystify such a conflict, this paper introduces a comprehensive benchmark to measure and evaluate GNNs' capability in capturing and leveraging the information encoded in different frequency components of the input graph data.
Instance-Aware Graph Prompt Learning
Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner.
Invariant Shape Representation Learning For Image Classification
In this paper, we introduce a novel framework that for the first time develops invariant shape representation learning (ISRL) to further strengthen the robustness of image classifiers.
Federated Graph Learning with Graphless Clients
To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client.
A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation
Consequently, there has been a surge in research on graph machine learning under distribution shifts, aiming to train models to achieve satisfactory performance on out-of-distribution (OOD) test data.
Global Graph Counterfactual Explanation: A Subgraph Mapping Approach
Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated.
Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective for Molecular Property Prediction
In recent years, Graph Neural Networks (GNNs) have become successful in molecular property prediction tasks such as toxicity analysis.
Channel-Wise Mixed-Precision Quantization for Large Language Models
Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter sizes.
Federated Graph Learning with Structure Proxy Alignment
Moreover, FGL also encounters a unique challenge for the node classification task: the nodes from a minority class in a client are more likely to have biased neighboring information, which prevents FGL from learning expressive node embeddings with Graph Neural Networks (GNNs).
Understanding and Modeling Job Marketplace with Pretrained Language Models
Job marketplace is a heterogeneous graph composed of interactions among members (job-seekers), companies, and jobs.
Towards Certified Unlearning for Deep Neural Networks
In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency and strong theoretical guarantees.
Verification of Machine Unlearning is Fragile
These strategies enable data owners to ascertain whether their target data has been effectively unlearned from the model.
IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks
Specifically, we first instantiate four types of unlearning requests on graphs, and then we propose an approximation approach to flexibly handle these unlearning requests over diverse GNNs.
A Benchmark for Fairness-Aware Graph Learning
Fairness-aware graph learning has gained increasing attention in recent years.
CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models
To address these limitations, we collect a variety of datasets designed for the bias evaluation of LLMs, and further propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models
Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-checking and information searching.
Causal Inference with Latent Variables: Recent Advances and Future Prospectives
Depending on the type of unobserved variables and the specific CI task, various consequences can be incurred if these latent variables are carelessly handled, such as biased estimation of causal effects, incomplete understanding of causal mechanisms, lack of individual-level causal consideration, etc.
Few-shot Knowledge Graph Relational Reasoning via Subgraph Adaptation
To overcome these challenges, we propose SAFER (Subgraph Adaptation for Few-shot Relational Reasoning), a novel approach that effectively adapts the information in contextualized graphs to various subgraphs generated from support and query triplets to perform the prediction.
Knowledge Graph-Enhanced Large Language Models via Path Selection
In addition, LLMs tend to pick only knowledge with direct semantic relationship with the input text, while potentially useful knowledge with indirect semantics can be ignored.
Cognitively Inspired Energy-Based World Models
One of the predominant methods for training world models is autoregressive prediction in the output space of the next element of a sequence.
FastGAS: Fast Graph-based Annotation Selection for In-Context Learning
By aggregating nodes from diverse pieces and annotating the corresponding instances, we identify a set of diverse and representative instances for ICL.
Spectral Greedy Coresets for Graph Neural Networks
However, owing to the interdependence of graph nodes, coreset selection, which selects subsets of the data examples, has not been successfully applied to speed up GNN training on large graphs, warranting special treatment.
Safety in Graph Machine Learning: Threats and Safeguards
In this survey paper, we explore three critical aspects vital for enhancing safety in Graph ML: reliability, generalizability, and confidentiality.
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.
GraphRCG: Self-Conditioned Graph Generation
In contrast, in this work, we propose a novel self-conditioned graph generation framework designed to explicitly model graph distributions and employ these distributions to guide the generation process.
Large Language Models for Data Annotation and Synthesis: A Survey
Furthermore, this survey includes an in-depth taxonomy of data types that LLMs can annotate, a comprehensive review of learning strategies for models utilizing LLM-generated annotations, and a detailed discussion of the primary challenges and limitations associated with using LLMs for data annotation and synthesis.
Efficient Prompt Optimization Through the Lens of Best Arm Identification
TRIPLE is built on a novel connection established between prompt optimization and fixed-budget best arm identification (BAI-FB) in multi-armed bandits (MAB); thus, it is capable of leveraging the rich toolbox from BAI-FB systematically and also incorporating unique characteristics of prompt optimization.
Personalized Federated Learning with Attention-based Client Selection
FedACS integrates an attention mechanism to enhance collaboration among clients with similar data distributions and mitigate the data scarcity issue.
Interpreting Pretrained Language Models via Concept Bottlenecks
Pretrained language models (PLMs) have made significant strides in various natural language processing tasks.
Certified Defense on the Fairness of Graph Neural Networks
Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks over the years.
Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance
Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing.
Collaborative Large Language Model for Recommender Systems
We first extend the vocabulary of pretrained LLMs with user/item ID tokens to faithfully model user/item collaborative and content semantics.
Knowledge Editing for Large Language Models: A Survey
Afterward, we provide an innovative taxonomy of KME techniques based on how the new knowledge is introduced into pre-trained LLMs, and investigate existing KME strategies while analyzing key insights, advantages, and limitations of methods from each category.
Marginal Nodes Matter: Towards Structure Fairness in Graphs
Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks.
ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt
Based on this framework, we propose a prompt-based transferability test to find the most relevant pretext task in order to reduce the semantic gap.
Adversarial Attacks on Fairness of Graph Neural Networks
Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e. g., female) in graph-based applications.
Fair Few-shot Learning with Auxiliary Sets
These auxiliary sets contain several labeled training samples that can enhance the model performance regarding fairness in meta-test tasks, thereby allowing for the transfer of learned useful fairness-oriented knowledge to meta-test tasks.
GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction
By considering embeddings encompassing graph topology and attribute information as reconstruction targets, our model could capture more generalized and comprehensive knowledge.
Collaborative Graph Neural Networks for Attributed Network Embedding
Graph neural networks (GNNs) have shown prominent performance on attributed network embedding.
Learning for Counterfactual Fairness from Observational Data
A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data.
A Look into Causal Effects under Entangled Treatment in Graphs: Investigating the Impact of Contact on MRSA Infection
In this paper, we study the problem of causal effect estimation with treatment entangled in a graph.
Contrastive Meta-Learning for Few-shot Node Classification
First, we propose to enhance the intra-class generalizability by involving a contrastive two-step optimization in each episode to explicitly align node embeddings in the same classes.
Federated Few-shot Learning
In this way, the server can exploit the computational power of all clients and train the model on a larger set of data samples among all clients.
Path-Specific Counterfactual Fairness for Recommender Systems
But since sensitive features may also affect user interests in a fair manner (e. g., race on culture-based preferences), indiscriminately eliminating all the influences of sensitive features inevitably degenerate the recommendations quality and necessary diversities.
Spatial-Temporal Networks for Antibiogram Pattern Prediction
In this paper, we propose a novel problem of antibiogram pattern prediction that aims to predict which patterns will appear in the future.
When Newer is Not Better: Does Deep Learning Really Benefit Recommendation From Implicit Feedback?
In recent years, neural models have been repeatedly touted to exhibit state-of-the-art performance in recommendation.
Few-shot Node Classification with Extremely Weak Supervision
Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i. e., meta-training classes) and then generalize to classes with limited labeled nodes (i. e., meta-test classes).
Causal Inference in Recommender Systems: A Survey of Strategies for Bias Mitigation, Explanation, and Generalization
Traditional RSs estimate user interests and predict their future behaviors by utilizing correlations in the observational historical activities, their profiles, and the content of interacted items.
RELIANT: Fair Knowledge Distillation for Graph Neural Networks
Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i. e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i. e., the teacher GNN model).
Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification
More recently, inspired by the development of graph self-supervised learning, transferring pretrained node embeddings for few-shot node classification could be a promising alternative to meta-learning but remains unexposed.
Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes.
Graph Few-shot Learning with Task-specific Structures
Therefore, to adaptively learn node representations across meta-tasks, we propose a novel framework that learns a task-specific structure for each meta-task.
CLEAR: Generative Counterfactual Explanations on Graphs
Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?".
Contrastive Graph Few-Shot Learning
Later, the trained encoder is frozen as a teacher model to distill a student model with a contrastive loss.
BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency
In addition, given the stealing behavior of novel Twitter bots, BIC proposes to model semantic consistency in tweets based on attention weights while using it to augment the decision process.
KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion
Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the \textit{de-facto} standard for knowledge graph completion.
Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications
Federated Graph Machine Learning (FGML) is a promising solution to tackle this challenge by training graph machine learning models in a federated manner.
Learning Causal Effects on Hypergraphs
Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes.
On Structural Explanation of Bias in Graph Neural Networks
The low transparency on how the structure of the input network influences the bias in GNN outcome largely limits the safe adoption of GNNs in various decision-critical scenarios.
Task-Adaptive Few-shot Node Classification
Then we transfer such knowledge to the classes with limited labeled nodes via our proposed task-adaptive modules.
BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
To bridge this gap, we present--to the best of our knowledge--the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights.
TwiBot-22: Towards Graph-Based Twitter Bot Detection
Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse.
Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage
Motivated by our analysis, we propose Fair View Graph Neural Network (FairVGNN) to generate fair views of features by automatically identifying and masking sensitive-correlated features considering correlation variation after feature propagation.
Towards Explanation for Unsupervised Graph-Level Representation Learning
Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}"
FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs
Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set.
Empowering Next POI Recommendation with Multi-Relational Modeling
Noticeably, LBSNs have offered unparalleled access to abundant heterogeneous relational information about users and POIs (including user-user social relations, such as families or colleagues; and user-POI visiting relations).
Fairness in Graph Mining: A Survey
Recently, algorithmic fairness has been extensively studied in graph-based applications.
KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media
Previous approaches generally focus on leveraging textual content to identify stances, while they fail to reason with background knowledge or leverage the rich semantic and syntactic textual labels in news articles.
Self-Supervised Learning for Recommender Systems: A Survey
In recent years, neural architecture-based recommender systems have achieved tremendous success, but they still fall short of expectation when dealing with highly sparse data.
Few-Shot Learning on Graphs
In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge.
Geometric Graph Representation Learning via Maximizing Rate Reduction
Learning discriminative node representations benefits various downstream tasks in graph analysis such as community detection and node classification.
Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective
Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph.
Learning Fair Node Representations with Graph Counterfactual Fairness
In this framework, we generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes.
Unbiased Graph Embedding with Biased Graph Observations
In this paper, we propose a principled new way for unbiased graph embedding by learning node embeddings from an underlying bias-free graph, which is not influenced by sensitive node attributes.
Second-Order Unsupervised Feature Selection via Knowledge Contrastive Distillation
Unsupervised feature selection aims to select a subset from the original features that are most useful for the downstream tasks without external guidance information.
Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation
Technically, for (1), a hierarchical hypergraph convolutional network based on the user- and group-level hypergraphs is developed to model the complex tuplewise correlations among users within and beyond groups.
EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
We then develop a framework EDITS to mitigate the bias in attributed networks while maintaining the performance of GNNs in downstream tasks.
Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification
Graphs are widely used to model the relational structure of data, and the research of graph machine learning (ML) has a wide spectrum of applications ranging from drug design in molecular graphs to friendship recommendation in social networks.
Fairness-Aware Unsupervised Feature Selection
Feature selection is a prevalent data preprocessing paradigm for various learning tasks.
Assessing the Causal Impact of COVID-19 Related Policies on Outbreak Dynamics: A Case Study in the US
Besides, as the confounders may be time-varying during COVID-19 (e. g., vigilance of residents changes in the course of the pandemic), it is even more difficult to capture them.
AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
Existing efforts can be mainly categorized as spectral-based and spatial-based methods.
Automated Generation of Interorganizational Disaster Response Networks through Information Extraction
When a disaster occurs, maintaining and restoring community lifelines subsequently require collective efforts from various stakeholders.
Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation
In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations.
Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
Text classification is a critical research topic with broad applications in natural language processing.
Line Graph Neural Networks for Link Prediction
In this formalism, a link prediction problem is converted to a graph classification task.
Graph Prototypical Networks for Few-shot Learning on Attributed Networks
By constructing a pool of semi-supervised node classification tasks to mimic the real test environment, GPN is able to perform \textit{meta-learning} on an attributed network and derive a highly generalizable model for handling the target classification task.
Scalable Attack on Graph Data by Injecting Vicious Nodes
Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations.
Enhancing Social Recommendation with Adversarial Graph Convolutional Networks
Social recommender systems are expected to improve recommendation quality by incorporating social information when there is little user-item interaction data.
Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective
In general, two lines of research have been conducted, and their common ideas can be summarized as follows: (1) for the data noise issue, adversarial perturbations and adversarial sampling-based training often serve as a solution; (2) for the data sparsity issue, data augmentation--implemented by capturing the distribution of real data under the minimax framework--is the primary coping strategy.
Counterfactual Evaluation of Treatment Assignment Functions with Networked Observational Data
When such data comes with network information, the later can be potentially useful to correct hidden confounding bias.
Generating Reliable Friends via Adversarial Training to Improve Social Recommendation
Most of the recent studies of social recommendation assume that people share similar preferences with their friends and the online social relations are helpful in improving traditional recommender systems.
Feature Interaction-aware Graph Neural Networks
Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on different graph learning tasks.
Deep Structured Cross-Modal Anomaly Detection
To this end, we propose a novel deep structured anomaly detection framework to identify the cross-modal anomalies embedded in the data.
SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks
SpecAE leverages Laplacian sharpening to amplify the distances between representations of anomalies and the ones of the majority.
Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
Machine learning models are currently being deployed in a variety of real-world applications where model predictions are used to make decisions about healthcare, bank loans, and numerous other critical tasks.
Learning Individual Causal Effects from Networked Observational Data
In fact, an important fact ignored by the majority of previous work is that observational data can come with network information that can be utilized to infer hidden confounders.
Deep Anomaly Detection on Attributed Networks
In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data.
Online Newton Step Algorithm with Estimated Gradient
In particular, we extend the ONS algorithm with the trick of expected gradient and develop a novel second-order online learning algorithm, i. e., Online Newton Step with Expected Gradient (ONSEG).
A Survey of Learning Causality with Data: Problems and Methods
This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations.
Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximation
As opposed to manual feature engineering which is tedious and difficult to scale, network representation learning has attracted a surge of research interests as it automates the process of feature learning on graphs.
Attributed Network Embedding for Learning in a Dynamic Environment
To our best knowledge, we are the first to tackle this problem with the following two challenges: (1) the inherently correlated network and node attributes could be noisy and incomplete, it necessitates a robust consensus representation to capture their individual properties and correlations; (2) the embedding learning needs to be performed in an online fashion to adapt to the changes accordingly.
Challenges of Feature Selection for Big Data Analytics
We are surrounded by huge amounts of large-scale high dimensional data.
Feature Selection: A Data Perspective
To facilitate and promote the research in this community, we also present an open-source feature selection repository that consists of most of the popular feature selection algorithms (\url{http://featureselection. asu. edu/}).
