Search Results for author:
Found 226 papers, 144 papers with code
Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
Our analysis further highlights the importance of both instance-level normalization and iterative optimization of selected data for balanced learning of diverse capabilities.
Hierarchical Superpixel Segmentation via Structural Information Theory
Superpixel segmentation is a foundation for many higher-level computer vision tasks, such as image segmentation, object recognition, and scene understanding.
Prompt-based Unifying Inference Attack on Graph Neural Networks
Specifically, ProIA retains the crucial topological information of the graph during pre-training, enhancing the background knowledge of the inference attack model.
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
This paper introduces LongBench v2, a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks.
SocialED: A Python Library for Social Event Detection
SocialED is a comprehensive, open-source Python library designed to support social event detection (SED) tasks, integrating 19 detection algorithms and 14 diverse datasets.
Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space
Specifically, the proposed framework first models social messages into semantic-based message anchors, and then leverages the structure of the anchor graph and the expressiveness of the hyperbolic space to acquire structure- and geometry-aware anchor representations.
Structural Entropy Guided Probabilistic Coding
Probabilistic embeddings have several advantages over deterministic embeddings as they map each data point to a distribution, which better describes the uncertainty and complexity of data.
Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems
Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other.
Free Process Rewards without Process Labels
The only assumption is to parameterize the outcome reward as the log-likelihood ratios of the policy and reference models, which can be optimized regardless of the specific choice of loss objectives.
Multi-View Incongruity Learning for Multimodal Sarcasm Detection
Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL's advancement in mitigating the effect of spurious correlation.
Constraint Back-translation Improves Complex Instruction Following of Large Language Models
Following the conventional instruction-tuning practice, previous works conduct post-training on complex instruction-response pairs generated by feeding complex instructions to advanced LLMs.
Spiking Graph Neural Network on Riemannian Manifolds
Extensive experiments on common graphs show the proposed MSG achieves superior performance to previous spiking GNNs and energy efficiency to conventional GNNs.
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models.
Pre-training Distillation for Large Language Models: A Design Space Exploration
Previous work applying KD in the field of large language models (LLMs) typically focused on the post-training phase, where the student LLM learns directly from instructions and corresponding responses generated by the teacher model.
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
However, edge deployment of proprietary LLMs introduces new security threats: attackers who obtain an edge-deployed LLM can easily use it as a base model for various tasks due to its high generalization ability, which we call foundational capability stealing.
Effective Exploration Based on the Structural Information Principles
Traditional information theory provides a valuable foundation for Reinforcement Learning, particularly through representation learning and entropy maximization for agent exploration.
FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
Practically, both the detection and mitigation models in FactCheckMate are lightweight, adding little inference overhead; FactCheckMate proves a more efficient approach for mitigating hallucinations compared to many post-hoc alternatives.
A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by training on long-context data, followed by architectural modifications to reduce the overhead of KV cache during serving.
DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism
We present a novel local aggregation strategy utilizing Bayesian optimization to incorporate global knowledge while retaining local characteristics.
Multivariate Time-Series Anomaly Detection based on Enhancing Graph Attention Networks with Topological Analysis
Additionally, we present an augmented GAT to manage complex inter-feature dependencies, which incorporates graph topology into node features across multiple scales, a versatile, plug-and-play enhancement that significantly boosts the performance of GAT.
OpenEP: Open-Ended Future Event Prediction
For question construction, we pose questions from seven perspectives, including location, time, event development, event outcome, event impact, event response, and other, to facilitate an in-depth analysis and understanding of the comprehensive evolution of events.
S2-Attention: Hardware-Aware Context Sharding Among Attention Heads
S2-Attention achieves wall-clock speedup of 8. 79X, 15. 87X, 25. 3X compared to the strong FlashAttention-2 baseline with strong downstream performance on-par with full attention and perfect retrieval performance at a 128k context length.
OpenHands: An Open Platform for AI Software Developers as Generalist Agents
OpenDevin), a platform for the development of powerful and flexible AI agents that interact with the world in similar ways to those of a human developer: by writing code, interacting with a command line, and browsing the web.
Table-Filling via Mean Teacher for Cross-domain Aspect Sentiment Triplet Extraction
This allows the model to benefit from the OD extraction paradigm and region-level alignment.
Adaptive Differentially Private Structural Entropy Minimization for Unsupervised Social Event Detection
In this process, our method can adaptively apply differential privacy based on the events occurring each day in an open environment to maximize the use of the privacy budget.
MAVEN-Fact: A Large-scale Event Factuality Detection Dataset
Thanks to the comprehensive annotations of event arguments and relations in MAVEN, MAVEN-Fact also supports some further analyses and we find that adopting event arguments and relations helps in event factuality detection for fine-tuned models but does not benefit LLMs.
SciCode: A Research Coding Benchmark Curated by Scientists
Since language models (LMs) now outperform average humans on many challenging tasks, it has become increasingly difficult to develop challenging, high-quality, and realistic evaluations.
SOLO: A Single Transformer for Scalable Vision-Language Modeling
We present SOLO, a single transformer for Scalable visiOn-Language mOdeling.
Eliminating Position Bias of Language Models: A Mechanistic Approach
Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context.
GC-Bench: An Open and Unified Benchmark for Graph Condensation
To fill this gap, we develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation in different scenarios systematically.
IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning
Deep graph learning has gained grand popularity over the past years due to its versatility and success in representing graph data across a wide range of domains.
$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
Recent findings demonstrate that on-policy data is the key to successful preference learning, where the preference data is collected using the same policy LM being trained.
M&M VTO: Multi-Garment Virtual Try-On and Editing
We present M&M VTO, a mix and match virtual try-on method that takes as input multiple garment images, text description for garment layout and an image of a person.
Promotional Language and the Adoption of Innovative Ideas in Science
How are the merits of innovative ideas communicated in science?
R-ODE: Ricci Curvature Tells When You Will be Informed
Such limitation motivates us to pose the problem of the time-aware personalized information diffusion prediction for the first time, telling the time when the target user will be informed.
LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
DSI is also theoretically presented as a new graph clustering objective, not requiring the predefined cluster number.
SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detection
Recent advancements in social bot detection have been driven by the adoption of Graph Neural Networks.
Event GDR: Event-Centric Generative Document Retrieval
Inspired by this, we propose Event GDR, an event-centric generative document retrieval model, integrating event knowledge into this task.
ADELIE: Aligning Large Language Models on Information Extraction
Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks.
Hyperbolic Geometric Latent Diffusion Model for Graph Generation
Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation.
Retrieval Head Mechanistically Explains Long-Context Factuality
Despite the recent progress in long-context language models, it remains elusive how transformer-based models exhibit the capability to retrieve relevant information from arbitrary locations within the long context.
BotDGT: Dynamicity-aware Social Bot Detection with Dynamic Graph Transformers
To tackle these challenges, we propose BotDGT, a novel framework that not only considers the topological structure, but also effectively incorporates dynamic nature of social network.
Effective Reinforcement Learning Based on Structural Information Principles
An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge.
Relational Prompt-based Pre-trained Language Models for Social Event Detection
In this paper, we approach social event detection from a new perspective based on Pre-trained Language Models (PLMs), and present RPLM_SED (Relational prompt-based Pre-trained Language Models for Social Event Detection).
Advancing LLM Reasoning Generalists with Preference Trees
We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning.
Source-Aware Training Enables Knowledge Attribution in Language Models
We investigate the problem of intrinsic source citation, where LLMs are required to cite the pretraining source supporting a generated response.
Instruction-based Hypergraph Pretraining
However, the gap between training objectives and the discrepancy between data distributions in pretraining and downstream tasks hinders the transfer of the pretrained knowledge.
Understanding the PULSAR Effect in Combined Radiotherapy and Immunotherapy through Attention Mechanisms with a Transformer Model
PULSAR (personalized, ultra-fractionated stereotactic adaptive radiotherapy) is the adaptation of stereotactic ablative radiotherapy towards personalized cancer management.
Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character role-playing (MCRP) scenarios.
Event-level Knowledge Editing
However, natural knowledge updates in the real world come from the occurrences of new events rather than direct changes in factual triplets.
Data Engineering for Scaling Language Models to 128K Context
We demonstrate that continual pretraining of the full model on 1B-5B tokens of such data is an effective and affordable strategy for scaling the context length of language models to 128K.
PULSAR Effect: Revealing Potential Synergies in Combined Radiation Therapy and Immunotherapy via Differential Equations
Therefore, a synergistic effect between immunotherapy and PULSAR is observed when the pulses are spaced out by a certain number of days.
Executable Code Actions Elicit Better LLM Agents
LLM agents are typically prompted to produce actions by generating JSON or text in a pre-defined format, which is usually limited by constrained action space (e. g., the scope of pre-defined tools) and restricted flexibility (e. g., inability to compose multiple tools).
DARCS: Memory-Efficient Deep Compressed Sensing Reconstruction for Acceleration of 3D Whole-Heart Coronary MR Angiography
While unrolling-based deep reconstruction methods have achieved state-of-the-art performance on 2D image reconstruction, their application to 3D reconstruction is hindered by the large amount of memory needed to train an unrolled network.
DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing
Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph.
CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification
Additionally, acknowledging the complementary nature of semantic details across different modalities, we integrate text features from the bimodal language descriptions to achieve comprehensive semantics.
Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learning
In light of the issues above, we propose the problem of \emph{Motif-aware Riemannian Graph Representation Learning}, seeking a numerically stable encoder to capture motif regularity in a diverse-curvature manifold without labels.
Mathematical Modeling of the Synergetic Effect between Radiotherapy and Immunotherapy
Achieving effective synergy between radiotherapy and immunotherapy is critical for optimizing tumor control and treatment outcomes.
Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection
As a trending approach for social event detection, graph neural network (GNN)-based methods enable a fusion of natural language semantics and the complex social network structural information, thus showing SOTA performance.
Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding
Specifically, PoinDP first learns the hierarchy weights for each entity based on the Poincar\'e model in hyperbolic space.
Semi-Supervised Clustering via Structural Entropy with Different Constraints
In this work, we present Semi-supervised clustering via Structural Entropy (SSE), a novel method that can incorporate different types of constraints from diverse sources to perform both partitioning and hierarchical clustering.
Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) is an emerging task to extract a given sentence's triplets, which consist of aspects, opinions, and sentiments.
Catwalk: A Unified Language Model Evaluation Framework for Many Datasets
The success of large language models has shifted the evaluation paradigms in natural language processing (NLP).
Adversarial Socialbots Modeling Based on Structural Information Principles
The importance of effective detection is underscored by the fact that socialbots imitate human behavior to propagate misinformation, leading to an ongoing competition between socialbots and detectors.
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e. g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance.
Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge
Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses?
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-event relationships.
When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks
In this paper, we find that ICL falls short of handling specification-heavy tasks, which are tasks with complicated and extensive task specifications, requiring several hours for ordinary humans to master, such as traditional information extraction tasks.
RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) is dedicated to forecasting the sentiment polarity of aspect terms within sentences.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction
Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text.
MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization
Based on this, we propose a relative structural entropy-based position encoding and a multi-head attention masking scheme based on multi-layer encoding trees.
Uncertainty-guided Boundary Learning for Imbalanced Social Event Detection
While in our observation, compared to the rarity of classes, the calibrated uncertainty estimated from well-trained evidential deep learning networks better reflects model performance.
Language Models Hallucinate, but May Excel at Fact Verification
Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs).
Knowledge Graph Context-Enhanced Diversified Recommendation
Collectively, our contributions signify a substantial stride towards augmenting the panorama of recommendation diversity within the realm of KG-informed RecSys paradigms.
Unified Pretraining for Recommendation via Task Hypergraphs
On the other hand, pretraining and finetuning on the same dataset leads to a high risk of overfitting.
Multi-omics Sampling-based Graph Transformer for Synthetic Lethality Prediction
We showcase the effectiveness of MSGT-SL on real-world SL tasks, demonstrating the empirical benefits gained from the graph transformer and multi-omics data.
Privacy in Large Language Models: Attacks, Defenses and Future Directions
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines.
FiLM: Fill-in Language Models for Any-Order Generation
Language models have become the backbone of today's AI systems.
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
We propose Trust Region Aware Minimization (TRAM), a SAM algorithm fine-tuning for low parameter sharpness and smooth, informative representations preserving pre-trained structure.
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks.
OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding
Event understanding aims at understanding the content and relationship of events within texts, which covers multiple complicated information extraction tasks: event detection, event argument extraction, and event relation extraction.
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
However, current evaluation protocols often emphasize benchmark performance with single-turn exchanges, neglecting the nuanced interactions among the user, LLMs, and external tools, while also underestimating the importance of natural language feedback from users.
Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphs
In this work, we propose a novel unsupervised Skin Lesion sEgmentation framework based on structural entropy and isolation forest outlier Detection, namely SLED.
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
As a result, their performance suffers drastically on inputs longer than those encountered during training, substantially limiting their applications in real-world tasks involving long contexts such as encoding scientific articles, code repositories, or long dialogues.
Group Identification via Transitional Hypergraph Convolution with Cross-view Self-supervised Learning
With the proliferation of social media, a growing number of users search for and join group activities in their daily life.
Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation
In response, we introduce Pentathlon, a benchmark for holistic and realistic evaluation of model efficiency.
Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation
We explore the role of the fine-grained item attributes in bridging the gaps between the existing and the SCS items and pre-train a knowledgeable item-attribute graph for SCS item recommendation.
Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity
We then propose a novel Singular sPectrum sMoothing regularization for Recommendation (SPMRec), which acts as a controllable surrogate to alleviate the degeneration and achieve the balance between recommendation diversity and performance.
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation
In this paper, we check the reliability of EE evaluations and identify three major pitfalls: (1) The data preprocessing discrepancy makes the evaluation results on the same dataset not directly comparable, but the data preprocessing details are not widely noted and specified in papers.
Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
As large language models (LLMs) are continuously being developed, their evaluation becomes increasingly important yet challenging.
LeTI: Learning to Generate from Textual Interactions
We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback.
Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
We study whether multiple large language models (LLMs) can autonomously improve each other in a negotiation game by playing, reflecting, and criticizing.
Contrastive Graph Clustering in Curvature Spaces
On the other hand, contrastive learning boosts the deep graph clustering but usually struggles in either graph augmentation or hard sample mining.
Hierarchical State Abstraction Based on Structural Information Principles
State abstraction optimizes decision-making by ignoring irrelevant environmental information in reinforcement learning with rich observations.
Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification
We find that training labeled nodes with different hierarchical properties have a significant impact on the node classification tasks and confirm it in our experiments.
Graph Collaborative Signals Denoising and Augmentation for Recommendation
Moreover, we show that the inclusion of user-user and item-item correlations can improve recommendations for users with both abundant and insufficient interactions.
Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles
Role-based learning is a promising approach to improving the performance of Multi-Agent Reinforcement Learning (MARL).
SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
Graph Neural Networks (GNNs) are de facto solutions to structural data learning.
FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detection
In particular, a global generator is used to extract the knowledge of global data distribution and distill it into each client's local model.
Reinforcement Learning Guided Multi-Objective Exam Paper Generation
To reduce the repetitive and complex work of instructors, exam paper generation (EPG) technique has become a salient topic in the intelligent education field, which targets at generating high-quality exam paper automatically according to instructor-specified assessment criteria.
A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
This study provides a comprehensive review of recent research advancements, challenges, and opportunities for PFMs in text, image, graph, as well as other data modalities.
A Comprehensive Survey on Automatic Knowledge Graph Construction
A knowledge graph is built in three steps: knowledge acquisition, knowledge refinement, and knowledge evolution.
Specializing Smaller Language Models towards Multi-Step Reasoning
by paying the price of decreased generic ability, we can clearly lift up the scaling curve of models smaller than 10B towards a specialized multi-step math reasoning ability.
Unbiased and Efficient Self-Supervised Incremental Contrastive Learning
Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning.
Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation
Wasserstein Discrepancy Measurement builds upon the 2-Wasserstein distance, which is more robust, more efficient in small batch sizes, and able to model the uncertainty of stochastic augmentation processes.
Parallel Multi-Extended State Observers based {ADRC} with Application to High-Speed Precision Motion Stage
In particular, the algorithm for calculating the tracking error caused by single ESO's estimation error is constructed.
State of the Art and Potentialities of Graph-level Learning
Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures.
Self-organization Preserved Graph Structure Learning with Principle of Relevant Information
Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships.
Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces
On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the coming graph sequence.
MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
It contains 103, 193 event coreference chains, 1, 216, 217 temporal relations, 57, 992 causal relations, and 15, 841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude.
COPEN: Probing Conceptual Knowledge in Pre-trained Language Models
We believe this is a critical bottleneck for realizing human-like cognition in PLMs.
How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers
Our results motivate research on simpler alternatives to input-dependent attention, as well as on methods for better utilization of this mechanism in the Transformer architecture.
Ranking-based Group Identification via Factorized Attention on Social Tripartite Graph
PA layers efficiently learn the relatedness of non-neighbor nodes to improve the information propagation to users.
Sequential Recommendation with Auxiliary Item Relationships via Multi-Relational Transformer
However, it remains a significant challenge to model auxiliary item relationships in SR. To simultaneously model high-order item-item transitions in sequences and auxiliary item relationships, we propose a Multi-relational Transformer capable of modeling auxiliary item relationships for SR (MT4SR).
DAGAD: Data Augmentation for Graph Anomaly Detection
To bridge the gaps, this paper devises a novel Data Augmentation-based Graph Anomaly Detection (DAGAD) framework for attributed graphs, equipped with three specially designed modules: 1) an information fusion module employing graph neural network encoders to learn representations, 2) a graph data augmentation module that fertilizes the training set with generated samples, and 3) an imbalance-tailored learning module to discriminate the distributions of the minority (anomalous) and majority (normal) classes.
Modeling Context With Linear Attention for Scalable Document-Level Translation
Document-level machine translation leverages inter-sentence dependencies to produce more coherent and consistent translations.
Transparency Helps Reveal When Language Models Learn Meaning
Many current NLP systems are built from language models trained to optimize unsupervised objectives on large amounts of raw text.
Complexity-Based Prompting for Multi-Step Reasoning
In this work, we propose complexity-based prompting, a simple and effective example selection scheme for multi-step reasoning.
Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation
To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology.
Information Extraction and Human-Robot Dialogue towards Real-life Tasks: A Baseline Study with the MobileCS Dataset
Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected through Wizard-of-Oz simulated games.
Cross-Network Social User Embedding with Hybrid Differential Privacy Guarantees
Integrating multiple online social networks (OSNs) has important implications for many downstream social mining tasks, such as user preference modelling, recommendation, and link prediction.
A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
To bridge this gap, we make the first attempt to study the problem of self-supervised temporal graph representation learning in the general Riemannian space, supporting the time-varying curvature to shift among hyperspherical, Euclidean and hyperbolic spaces.
Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing
Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology positions of labeled nodes, which significantly damages the performance of GNNs.
Automating DBSCAN via Deep Reinforcement Learning
DBSCAN is widely used in many scientific and engineering fields because of its simplicity and practicality.
A Challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems
A challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems, Co-located with EMNLP2022 SereTOD Workshop.
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.
Graph-level Neural Networks: Current Progress and Future Directions
To frame this survey, we propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling.