Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks85 from public data
- Graph Self-Supervised Learning: A Survey786
A unified framework is constructed that mathematically formalizes the paradigm of graph SSL and describes the applications of graphSSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes ofgraph SSL.
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning537
This article presents a novel Contrastive self-supervised Learning framework for Anomaly detection on attributed networks (CoLA for abbreviation), which fully exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure in an unsupervised way.
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT411
This survey aims to shed light on the research of the PFMs on scalability, security, logical reasoning ability, cross-domain learning ability, cross-domain learning ability, and user-friendly interactive ability for artificial general intelligence.
- Graph Neural Networks for Graphs With Heterophily: A Survey343
A systematic taxonomy that governs existing heterophilic GNN models for heterophilic graphs is proposed, aiming to facilitate the development of more effective GNNs across a spectrum of practical applications and learning tasks in the graph research community.
- Towards Unsupervised Deep Graph Structure Learning299
A novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning is proposed, where the learned graph topology is optimized by data itself without any external guidance.
- Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection221
This paper proposes a novel method, Self-Supervised Learning for Graph Anomaly Detection (SL-GAD), which outperforms state-of-the-art methods by a large margin and employs two modules, generative attribute regression and multi-view contrastive learning for anomaly detection.
- 208
- MMVU: Measuring Expert-Level Multi-Discipline Video Understanding167
This work introduces $\color{Blue}{\text{MMVU}}$, a comprehensive expert-level, multi-discipline benchmark for evaluating foundation models in video understanding, and conducts an extensive evaluation of 36 frontier multimodal foundation models on $\color{Blue}{\text{MMVU}}$.
- 166
- Emerging trends in federated learning: from model fusion to federated X learning159
Various learning algorithms to improve the vanilla federated averaging algorithm are explored and model fusion methods such as adaptive aggregation, regularization, clustered methods, and Bayesian methods are reviewed.
- On Learning to Summarize with Large Language Models as References146
This work uses LLMs as both oracle summary generators for standard supervised fine-tuning and oracle summary evaluators for efficient contrastive learning that leverages the LLMs’ supervision signals to investigate whether their performance can be substantially improved.
- Towards Self-Interpretable Graph-Level Anomaly Detection104
A Self-Interpretable Graph aNomaly dETection model (SIGNET for short) that detects anomalous graphs as well as generates informative explanations simultaneously and is able to not only measure the abnormality of each graph based on cross-view mutual information but also provide informative graph rationales by extracting bottleneck subgraphs from the input graph and its dual hypergraph in a self-supervised way.
- GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection96
A new graph contrastive learning framework GOOD-D is developed, aiming at detecting OOD graphs solely based on unlabeled ID data, and a comprehensive benchmark is built to compare the proposed approach with different state-of-the-art methods.
- Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts83
This work discovers a system prompt leakage vulnerability in GPT-4V and proposes a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt), demonstrating the important role of system prompts in jailbreaking.
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning75
ARC is proposed, a generalist GAD approach that enables a ``one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly without the need for retraining or fine-tuning on the target dataset.
- Improving Large Language Model Fine-tuning for Solving Math Problems74
A fine-tuning recipe is designed that yields an 11.2% accuracy improvement over the few-shot performance of pre-trained PaLM 2-L model with majority voting and a multi-task sequential fine- Tuning, which integrates both solution generation and evaluation tasks together efficiently to enhance the LLM performance.
- Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation72
This work reframe MAS design as a conditional autoregressive graph generation task, where both the system composition and structure are designed jointly and proposes ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch.
- Learning Strong Graph Neural Networks with Weak Information70
D2PT is proposed, a dual-channel GNN framework that performs long-range information propagation not only on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
- 64
- 55
- On Learning Text Style Transfer with Direct Rewards45
This paper uses semantic similarity metrics originally used for fine-tuning neural machine translation models to explicitly assess the preservation of content between system outputs and input texts to explore training algorithms that instead optimize reward functions that explicitly consider different aspects of the style-transferred outputs.
- 44
- RefSum: Refactoring Neural Summarization44
This work highlights several limitations of previous methods and presents a new framework Refactor that provides a unified view of text summarization and summaries combination and can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements.
- PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection42
This work introduces a simple method termed PREprocessing and Matching, which eliminates the necessity for message-passing propagation during training, and employs a simple contrastive loss, leading to considerable reductions in training time and memory usage.
- M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models38
M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models, indicates that current foundation models still significantly underperform compared to human experts in multi-modal information retrieval and in reasoning across multiple scientific documents.
- Integrating Graphs With Large Language Models: Methods and Prospects37
This article discusses and proposes open questions for integrating LLMs with graph-structured data for the future direction of the field and underscores the pivotal role of graphs in advancing LLMs.
- Self-Supervision Improves Diffusion Models for Tabular Data Imputation29
This paper introduces an advanced diffusion model named SimpDM (SimpDM for brevity), specifically tailored for tabular data imputation tasks, and introduces a self-supervised alignment mechanism that aims to regularize the model, ensuring consistent and stable imputation predictions.
- Towards Data-centric Graph Machine Learning: Review and Outlook29
A systematic framework is introduced that encompasses all stages of the graph data lifecycle, including graph data collection, exploration, improvement, exploitation, and maintenance, and a thorough taxonomy of each stage is presented to answer three critical graph-centric questions.
- Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark28
A comprehensive evaluation framework that unifies GLAD and GLOD under the concept of generalized graph-level OOD detection is presented, a benchmark encompasses 35 datasets spanning four practical anomaly and OOD detection scenarios, facilitating the comparison of 18 representative GLAD/GLOD methods.
- Uncertainty-Aware Graph Neural Networks: A Multihop Evidence Fusion Approach27
A novel evidence-fusing graph neural network (EFGNN) is proposed to achieve trustworthy prediction, enhance node classification accuracy, and make explicit the risk of wrong predictions.
- AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research25
This work introduces AbGen, the first benchmark designed to evaluate the capabilities of LLMs in designing ablation studies for scientific research and develops AbGen-Eval, a meta-evaluation benchmark designed to assess the reliability of commonly used automated evaluation systems in measuring LLM performance on this task.
- mRNA Vaccines: Current Applications and Future Directions23
The mechanisms of tumor immune escape are discussed and the potential of mRNA vaccines to overcome tumor immune resistance is examined, projecting the future role of mRNA vaccines in cancer therapy.
- 23
- Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation20
A Gaussian model is introduced that utilizes a learnable "meta-representation" as a condition to estimate the expectation and variance of multi-hop propagated features via neural networks via neural networks, which captures the semantic and structural information underlying multiple propagated features but is naturally less susceptible to interference by noise.
- Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise20
A label-noise robust GNN that discards the coupled message-passing scheme and proposes a novel reliable graph pseudo labeling algorithm that can effectively leverage the knowledge of unlabeled nodes while mitigating the adverse effects of noisy pseudo labels.
- Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects19
Categorize existing GLA methods by their primary functions in LLM agent systems, including planning, memory, and tool usage, and then analyze how graphs and graph learning algorithms contribute to each, to highlight key future directions to advance this field.
- 19
- 16
- 16
- A Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization16
This paper investigates the recruitment of high-quality Amazon Mechanical Turk workers via a two-step pipeline and shows that it can successfully filter out subpar workers before they carry out the evaluations and obtain high-agreement annotations with similar constraints on resources.
- 16
- OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models15
OFA-MAS is proposed, a one-for-all framework that generates adaptive collaboration graphs for any task described in natural language through a single universal model, and Experiments show that OFA-MAS significantly outperforms specialized one-for-one models, generating highly adaptive MAS topologies.
- Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time15
A lightweight and plug-and-play Test-and-play Test-time adaptation framework for correcting Unseen Normal pattErns (TUNE) in GAD is proposed, which significantly enhances the generalizability of pre-trained GAD models to both synthetic and real unseen normal patterns.
- FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection14
FreeGAD is proposed, a novel training-free yet effective GAD method that leverages an affinity-gated residual encoder to generate anomaly-aware representations and achieves superior anomaly detection performance, efficiency, and scalability on multiple benchmark datasets from diverse domains, without any training or iterative optimization.
- DataLab: A Platform for Data Analysis and Intervention14
DataLab is a unified data-oriented platform that not only allows users to interactively analyze the characteristics of data but also provides a standardized interface so that many data processing operations can be provided within a unified interface.
- 14
- Backdoor Attacks to Pre-trained Unified Foundation Models13
This paper makes proof-of-concept level research on the backdoor attack for pre-trained unified foundation models and reveals the vulnerability of these models and suggests future research directions for enhancing the attack approach.
- 11
- 11
- 10
- 10
- Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling9
A novel method, derived from the theoretical framework of GIL, that achieves state-of-the-art performance, significantly outperforming existing methods across graph data from various domains and with different distribution shifts.
- Improving Interpretation Faithfulness for Vision Transformers9
This paper proposes a new method called Denoised Diffusion Smoothing (DDS), which adopts randomized smoothing and diffusion-based denoising and shows that processing ViTs directly with DDS can turn them into Faithful ViTs.
- Cyclic label propagation for graph semi-supervised learning9
This work introduces a novel framework for graph semi-supervised learning termed as Cyclic Label Propagation (CycProp for abbreviation), which integrates GNNs into the process of label propagation in a cyclic and mutually reinforcing manner to exploit the advantages of both GNN and LPA.
- 8
- 8
- EfficientLLM: Efficiency in Large Language Models6
This study systematically explores three key axes: architecture pretraining, fine-tuning, and inference, and generalize across modalities, which provides essential guidance for researchers and engineers navigating the efficiency-performance landscape of next-generation foundation models.
- Rethinking Efficient Multilingual Text Summarization Meta-Evaluation6
This work investigates an efficient multilingual meta-evaluation framework that uses machine translation systems to transform a monolingual meta-evaluation dataset into multilingual versions and identifies a two-stage evaluation method, which first translates multilingual texts into English and then performs evaluation.
- Data‐efficient graph learning: Problems, progress, and prospects6
This paper investigates a new research field—data‐efficient graph learning, which aims to push forward the performance boundary of graph ML models with different kinds of low‐cost supervision signals with different kinds of low‐cost supervision signals.
- 6
- QTSumm: Query-Focused Summarization over Tabular Data6
A new query-focused table summarization task, where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored summary, and proposes a new approach, named ReFactor, to retrieve and reason over query-relevant information from tabular data to generate several natural language facts.
- Unlearnable Graph: Protecting Graphs from Unauthorized Exploitation6
A novel method for generating unlearnable graph examples by injecting delusive but imperceptible noise into graphs using the authors' Error-Minimizing Structural Poisoning (EMinS) module, which is able to make the graphs unexploitable.
- 5
- GraphCloak: Safeguarding Task-specific Knowledge within Graph-structured Data from Unauthorized Exploitation5
GraphCloak is introduced to safeguard against the unauthorized usage of graph data by proposing two error-minimizing-based poisoning methods that target perturbations on the structural and feature space, along with a subgraph injection poisoning method.
- 4
- 3
- Design of an Encryption-Decryption Module Oriented for Internet Information Security SOC Design3
Two AES (Advanced Encryption Standard) cores are used to work in parallel, which improves the speed of the encryption module and improves the safety of data through the encryption-decryption chip and reduce the load of CPU.
- 2
- 2
- MaRU: A Manga Retrieval and Understanding System Connecting Vision and Language2
RU (Manga Retrieval and Understanding), a multi-staged system that connects vision and language to facilitate efficient search of both dialogues and scenes within Manga frames, exhibits promising results for scene retrieval.
- Review on Machine learning and its application in Atmospheric science and Human Behavior Recognition2
This paper mainly analyzes the application of machine learning in behavior recognition, meteorology and other industries, and summarizes the common methods and development status of machineLearning in these two industries.
- 1
- 1
- 1
- 1
- Training and Inference Methods for High-Coverage Neural Machine Translation1
A system built for the Duolingo Simultaneous Translation And Paraphrase for Language Education (STAPLE) shared task at the 4th Workshop on Neural Generation and Translation (WNGT 2020) and finds it is essential to deliberately expose the model to higher-quality translations more often during training for optimal translation performance.
- –
- –
- –
- MSRS: Evaluating Multi-Source Retrieval-Augmented Generation–
This work presents a scalable framework for constructing evaluation benchmarks that challenge RAG systems to integrate information across distinct sources and generate long-form responses, and finds that reasoning models significantly outperform standard LLMs at this distinct step.
- Construction of a new $$C^1$$ strictly monotone histogram interpolation spline curve–
A solution system for the specific form of the interpolation spline using Levenberg-Marquardt algorithm is presented and the effectiveness and robustness of the proposed spline curve are validated.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.