Search Results for author:
Found 149 papers, 93 papers with code
ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
In addition, we propose a knowledge-augmented baseline that integrates both human-annotated knowledge rules and implicit knowledge from large language models, enabling smaller models to achieve performance comparable to state-of-the-art LLMs.
VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
Each test case is a variant of a web platform, designed to be interactive, deployed in a realistic environment, and containing a visually embedded malicious prompt.
How Does Response Length Affect Long-Form Factuality
Large language models (LLMs) are widely used for long-form text generation.
MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
Recent advancements in AI agents have demonstrated their growing potential to drive and support scientific discovery.
Efficient Reasoning via Chain of Unconscious Thought
Inspired by UTT, we propose a new reasoning paradigm, termed Chain of Unconscious Thought (CoUT), to improve the token efficiency of LRMs by guiding them to mimic human unconscious thought and internalize reasoning processes.
Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
The real-world impact of misinformation stems from the underlying misleading narratives that creators seek to convey.
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Then, based on it, we cold-start our model's reasoning ability via SFT.
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.
Adapting Precomputed Features for Efficient Graph Condensation
To address this, Graph Condensation (GC) methods aim to compress large graphs into smaller, synthetic ones that are more manageable for GNN training.
Safety in Large Reasoning Models: A Survey
Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities.
Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
Recent advancements in visual language models (VLMs) have notably enhanced their capabilities in handling complex Graphical User Interface (GUI) interaction tasks.
FlowReasoner: Reinforcing Query-Level Meta-Agents
This paper proposes a query-level meta-agent named FlowReasoner to automate the design of query-level multi-agent systems, i. e., one system per user query.
Geneshift: Impact of different scenario shift on Jailbreaking LLM
Despite achieving the promising attack success rate using dictionary-based evaluation, existing jailbreak attack methods fail to output detailed contents to satisfy the harmful request, leading to poor performance on GPT-based evaluation.
Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs
Traditional Chinese Medicine (TCM) has seen increasing adoption in healthcare, with specialized Large Language Models (LLMs) emerging to support clinical applications.
Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models
Vision-language models (VLMs) have advanced rapidly in processing multimodal information, but their ability to reconcile conflicting signals across modalities remains underexplored.
How does Watermarking Affect Visual Language Models in Document Understanding?
Visual Language Models (VLMs) have become foundational models for document understanding tasks, widely used in the processing of complex multimodal documents across domains such as finance, law, and academia.
JudgeLRM: Large Reasoning Models as a Judge
The rise of Large Language Models (LLMs) as evaluators offers a scalable alternative to human annotation, yet existing Supervised Fine-Tuning (SFT) for judges approaches often fall short in domains requiring complex reasoning.
Efficient Inference for Large Reasoning Models: A Survey
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in complex task-solving.
Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack
Retrieval-augmented generation (RAG) systems enhance large language models by incorporating external knowledge, addressing issues like outdated internal knowledge and hallucination.
Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps
Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought.
RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs
Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data.
Ranked #1 on
Modality completion
on Amazon Baby
MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities.
Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization
However, we identify a critical limitation: not every adversarial optimization step leads to a positive outcome, and indiscriminately accepting optimization results at each step may reduce the overall attack success rate.
Words or Vision: Do Vision-Language Models Have Blind Faith in Text?
Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored.
Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
Large Language Models (LLMs) increasingly rely on prolonged reasoning chains to solve complex tasks.
Fact or Guesswork? Evaluating Large Language Model's Medical Knowledge with Structured One-Hop Judgment
Large language models (LLMs) have been widely adopted in various downstream task domains.
Navigating the Helpfulness-Truthfulness Trade-Off with Uncertainty-Aware Instruction Fine-Tuning
Instruction Fine-tuning (IFT) can enhance the helpfulness of Large Language Models (LLMs), but it may lower their truthfulness.
ReLearn: Unlearning via Learning for Large Language Models
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities.
Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
As large language models (LLMs) continue to evolve, ensuring their alignment with human goals and values remains a pressing challenge.
Enhancing LLM Character-Level Manipulation via Divide and Conquer
Large Language Models (LLMs) have demonstrated strong generalization capabilities across a wide range of natural language processing (NLP) tasks.
Lost in Edits? A $λ$-Compass for AIGC Provenance
Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content.
UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
Multimodal graphs (MMGs) represent such graphs where each node is associated with features from different modalities, while the edges capture the relationships between these entities.
GuardReasoner: Towards Reasoning-based LLM Safeguards
Then, we introduce reasoning SFT to unlock the reasoning capability of guard models.
CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
To address these challenges, in this work, we propose a Cross-modal Hierarchical Direct Preference Optimization (CHiP) to address these limitations.
Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and language tasks.
Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
Handcrafting heuristics for solving complex optimization tasks (e. g., route planning and task allocation) is a common practice but requires extensive domain knowledge.
Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation
Our results indicate that the optimal $K$ for certain modalities on specific datasets can be as low as 1 or 2, which may restrict the GNNs' capacity to capture global information.
Ranked #1 on
Multi-modal Recommendation
on Amazon Clothing
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues.
DRS: Deep Question Reformulation With Structured Output
Recent studies reveal that while LLMs can detect unanswerable questions, they struggle to assist users in reformulating these questions.
Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection
However, existing models primarily operate in a binary setting, and the anomaly scores they produce are usually based on the deviation of data points from normal data, which may not accurately reflect practical severity.
Partitioning Message Passing for Graph Fraud Detection
Label imbalance and homophily-heterophily mixture are the fundamental problems encountered when applying Graph Neural Networks (GNNs) to Graph Fraud Detection (GFD) tasks.
Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization
To resolve this question, we fully explore the potential of large language models on cross-lingual summarization task for low-resource languages through our four-step zero-shot method: Summarization, Improvement, Translation and Refinement (SITR) with correspondingly designed prompts.
Vulnerability of LLMs to Vertically Aligned Text Manipulations
Text classification involves categorizing a given text, such as determining its sentiment or identifying harmful content.
Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study over Open-ended Question Answering
Recent works integrating Knowledge Graphs (KGs) have led to promising improvements in enhancing reasoning accuracy of Large Language Models (LLMs).
FlipAttack: Jailbreak LLMs via Flipping
Second, we verify the strong ability of LLMs to perform the text-flipping task, and then develop 4 variants to guide LLMs to denoise, understand, and execute harmful behaviors accurately.
ID$^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition
This equivalence motivates an ID-preserving sampling algorithm, which operates over an adjusted gradient vector field, enabling the generation of fake face recognition datasets that approximate the distribution of real-world faces.
Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information.
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.
Multimodal Large Language Models for Phishing Webpage Detection and Identification
In this work, we take steps to study the efficacy of large language models (LLMs), in particular the multimodal LLMs, in detecting phishing webpages.
When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
Contrastive Language-Image Pre-training (CLIP) achieves remarkable performance in various downstream tasks through the alignment of image and text input embeddings and holds great promise for anomaly detection.
Ranked #3 on
Anomaly Detection
on One-class CIFAR-10
Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-Training on Industrial-Scale Data
Extensive experiments have demonstrated that our framework can perform pre-training on real-world web-scale graphs with over 540 million nodes and 12 billion edges and generalizes effectively to unseen new graphs with different downstream tasks.
RNA-FrameFlow: Flow Matching for de novo 3D RNA Backbone Design
We introduce RNA-FrameFlow, the first generative model for 3D RNA backbone design.
UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
However, existing Transformer models often fall short of capturing both intricate dependencies across variate and temporal dimensions in MTS data.
FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
A distinctive feature of our approach is its blend of natural language planning with beam search to optimize the selection of reasoning paths.
KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
Phishing attacks have inflicted substantial losses on individuals and businesses alike, necessitating the development of robust and efficient automated phishing detection approaches.
Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality.
UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
However, graph learning has predominantly focused on single-graph models, tailored to specific tasks or datasets, lacking the ability to transfer learned knowledge to different domains.
Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data.
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface.
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
In the face of uncertainty, the ability to *seek information* is of fundamental importance.
HiPA: Enabling One-Step Text-to-Image Diffusion Models via High-Frequency-Promoting Adaptation
The learned adaptors empower these diffusion models to generate high-quality images in just a single step.
Towards A Unified View of Answer Calibration for Multi-Step Reasoning
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities.
Efficient Heterogeneous Graph Learning via Random Projection
To achieve low information loss, we introduce a Relation-wise Neighbor Collection component with an Even-odd Propagation Scheme, which aims to collect information from neighbors in a finer-grained way.
Ranked #1 on
Heterogeneous Node Classification
on OAG-L1-Field
Primacy Effect of ChatGPT
We have two main findings: i) ChatGPT's decision is sensitive to the order of labels in the prompt; ii) ChatGPT has a clearly higher chance to select the labels at earlier positions as the answer.
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.
Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks
To address this, we introduce SheepDog, a style-robust fake news detector that prioritizes content over style in determining news veracity.
UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
To address these issues, we propose UniTime for effective cross-domain time series learning.
Ranked #5 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Multimodal Graph Learning for Generative Tasks
We study three research questions raised by MMGL: (1) how can we infuse multiple neighbor information into the pretrained LMs, while avoiding scalability issues?
Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights.
Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection
Despite considerable advances in automated fake news detection, due to the timely nature of news, it remains a critical open question how to effectively predict the veracity of news articles based on limited fact-checks.
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios.
A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions
However, these methods often suffer from data imbalance, a common issue in graph data where certain segments possess abundant data while others are scarce, thereby leading to biased learning outcomes.
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System
This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models.
LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
To mitigate these limitations, we introduce the LargeST benchmark dataset.
Proximity-Informed Calibration for Deep Neural Networks
We examine the problem over 504 pretrained ImageNet models and observe that: 1) Proximity bias exists across a wide variety of model architectures and sizes; 2) Transformer-based models are relatively more susceptible to proximity bias than CNN-based models; 3) Proximity bias persists even after performing popular calibration algorithms like temperature scaling; 4) Models tend to overfit more heavily on low proximity samples than on high proximity samples.
Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
With the advent of powerful large language models (LLMs) such as GPT or Llama2, which demonstrate an ability to reason and to utilize general knowledge, there is a growing need for techniques which combine the textual modelling abilities of LLMs with the structural learning capabilities of GNNs.
Ranked #3 on
Node Property Prediction
on ogbn-arxiv
(using extra training data)
GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
Label errors have been found to be prevalent in popular text, vision, and audio datasets, which heavily influence the safe development and evaluation of machine learning algorithms.
SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres
Event-centric structured prediction involves predicting structured outputs of events.
How Fragile is Relation Extraction under Entity Replacements?
In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context.
Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
Proposing an effective and flexible matrix to represent a graph is a fundamental challenge that has been explored from multiple perspectives, e. g., filtering in Graph Fourier Transforms.
Ranked #8 on
Graph Regression
on ZINC
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
To overcome this incoherence issue, we design a \emph{neighborhood agreement measure} between latent spaces and find that this agreement is surprisingly well-correlated with the reliability of a model's predictions.
TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks
To bridge this gap, we have constructed a real-world graph-based Traffic Accident Prediction (TAP) data repository, along with two representative tasks: accident occurrence prediction and accident severity prediction.
Scalable Neural Network Training over Distributed Graphs
We present RETEXO, the first framework which eliminates the severe communication bottleneck in distributed GNN training while respecting any given data partitioning configuration.
Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness
Trustworthy machine learning is of primary importance to the practical deployment of deep learning models.
Do We Really Need Graph Neural Networks for Traffic Forecasting?
Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting.
Probabilistic Knowledge Distillation of Face Ensembles
Mean ensemble (i. e. averaging predictions from multiple models) is a commonly-used technique in machine learning that improves the performance of each individual model.
A Generalization of ViT/MLP-Mixer to Graphs
First, they capture long-range dependency and mitigate the issue of over-squashing as demonstrated on Long Range Graph Benchmark and TreeNeighbourMatch datasets.
Ranked #6 on
Graph Regression
on Peptides-struct
Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation
How do we know when the predictions made by a classifier can be trusted?
Expanding Small-Scale Datasets with Guided Imagination
Specifically, GIF conducts data imagination by optimizing the latent features of the seed data in the semantically meaningful space of the prior model, resulting in the creation of photo-realistic images with new content.
Reachability-Aware Laplacian Representation in Reinforcement Learning
In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment.
MGNNI: Multiscale Graph Neural Networks with Implicit Layers
Recently, implicit graph neural networks (GNNs) have been proposed to capture long-range dependencies in underlying graphs.
Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph
We release all the open resources (OpenBG benchmarks) derived from it for the community and report experimental results of KG-centric tasks.
Joint Triplet Loss Learning for Next New POI Recommendation
Sparsity of the User-POI matrix is a well established problem for next POI recommendation, which hinders effective learning of user preferences.
Probing Spurious Correlations in Popular Event-Based Rumor Detection Benchmarks
As social media becomes a hotbed for the spread of misinformation, the crucial task of rumor detection has witnessed promising advances fostered by open-source benchmark datasets.
Flashlight: Scalable Link Prediction with Effective Decoders
However, HadamardMLP lacks the scalability for retrieving top scoring neighbors on large graphs, since to the best of our knowledge, there does not exist an algorithm to retrieve the top scoring neighbors for HadamardMLP decoders in sublinear complexity.
Neural PCA for Flow-Based Representation Learning
Without exploiting any label information, the principal components recovered store the most informative elements in their \emph{leading} dimensions and leave the negligible in the \emph{trailing} ones, allowing for clear performance improvements of $5\%$-$10\%$ in downstream tasks.
A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables
We propose $\mathcal{T}$ruth $\mathcal{T}$able net ($\mathcal{TT}$net), a novel Convolutional Neural Network (CNN) architecture that addresses, by design, the open challenges of interpretability, formal verification, and logic gate conversion.
ARES: Locally Adaptive Reconstruction-based Anomaly Scoring
However, the anomaly scoring function is not adaptive to the natural variation in reconstruction error across the range of normal samples, which hinders their ability to detect real anomalies.
GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction
GRAPHCACHE aggregates the features from sentences in the whole dataset to learn global representations of properties, and use them to augment the local features within individual sentences.
Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
In this paper, we propose the CORE (Counterfactual Analysis based Relation Extraction) debiasing method that guides the RE models to focus on the main effects of textual context without losing the entity information.
LPGNet: Link Private Graph Networks for Node Classification
In this paper, we present a new neural network architecture called LPGNet for training on graphs with privacy-sensitive edges.
Dangling-Aware Entity Alignment with Mixed High-Order Proximities
We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem.
MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
Based on a Markov process that trades off two types of distances, we present Markov Graph Diffusion Collaborative Filtering (MGDCF) to generalize some state-of-the-art GNN-based CF models.
Ranked #4 on
Multi-modal Recommendation
on Amazon Sports
EIGNN: Efficient Infinite-Depth Graph Neural Networks
Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN), to efficiently capture very long-range dependencies.
Information Extraction in Low-Resource Scenarios: Survey and Perspective
Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes.
The Geometry of Robust Value Functions
The key of this perspective is to decompose the value space, in a state-wise manner, into unions of hypersurfaces.
Time-Aware Neighbor Sampling for Temporal Graph Networks
In this work, we propose the TNS (Time-aware Neighbor Sampling) method: TNS learns from temporal information to provide an adaptive receptive neighborhood for every node at any time.
LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks
This allows us to introduce learnability into local outlier methods, in the form of a neural network, for greater flexibility and expressivity: specifically, we propose LUNAR, a novel, graph neural network-based anomaly detection method.
Probabilistic Contrastive Loss for Self-Supervised Learning
This paper proposes a probabilistic contrastive loss function for self-supervised learning.
Adaptive Data Augmentation on Temporal Graphs
To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information.
Structure-Aware Label Smoothing for Graph Neural Networks
Representing a label distribution as a one-hot vector is a common practice in training node classification models.
Benefit-aware Early Prediction of Health Outcomes on Multivariate EEG Time Series
Given a cardiac-arrest patient being monitored in the ICU (intensive care unit) for brain activity, how can we predict their health outcomes as early as possible?
SSMF: Shifting Seasonal Matrix Factorization
In general, given a data stream of events with seasonal patterns that innovate over time, how can we effectively and efficiently forecast future events?
Deep Long-Tailed Learning: A Survey
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution.
Truth Table Deep Convolutional Neural Network, A New SAT-Encodable Architecture - Application To Complete Robustness
Moreover, the corresponding SAT conversion method intrinsically leads to formulas with a large number of variables and clauses, impeding interpretability as well as formal verification scalability.
Explainable Artificial Intelligence (XAI)
Explanation Generation
+1
When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?
In view of this, one may ask: can we leverage the additional signals from contrastive learning to alleviate data scarcity, so as to benefit STG forecasting?
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.
Ranked #9 on
Long-tail Learning
on iNaturalist 2018
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
It enables learning high-quality Laplacian representations that faithfully approximate the ground truth.
GraphAnoGAN: Detecting Anomalous Snapshots from Attributed Graphs
Specifically, the generative model learns to approximate the distribution of anomalous samples from the candidate set of graph snapshots, and the discriminative model detects whether the sampled snapshot is from the ground-truth or not.
Spherical Confidence Learning for Face Recognition
Probabilistic Face Embeddings (PFE) is the first attempt to address this dilemma.
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
Given high-dimensional time series data (e. g., sensor data), how can we detect anomalous events, such as system faults and attacks?
Ranked #8 on
Unsupervised Anomaly Detection
on SMAP
Sketch-Based Anomaly Detection in Streaming Graphs
This higher-order sketch has the useful property of preserving the dense subgraph structure (dense subgraphs in the input turn into dense submatrices in the data structure).
MemStream: Memory-Based Streaming Anomaly Detection
Given a stream of entries over time in a multi-dimensional data setting where concept drift is present, how can we detect anomalous activities?
Mixup for Node and Graph Classification
In this work, we propose the Mixup methods for two fundamental tasks in graph learning: node and graph classification.
Ranked #16 on
Node Classification
on Pubmed
Isconna: Streaming Anomaly Detection with Frequency and Patterns
Isconna does not actively explore or maintain pattern snippets; it instead measures the consecutive presence and absence of edge records.
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
In this paper, we investigate whether applying contrastive learning to fine-tuning would bring further benefits, and analytically find that optimizing the contrastive loss benefits both discriminative representation learning and model optimization during fine-tuning.
Hypersphere Face Uncertainty Learning
To address these issues, in this paper, we propose a novel framework for face uncertainty learning in hyperspherical space.
Dynamic Graph-Based Anomaly Detection in the Electrical Grid
Given sensor readings over time from a power grid, how can we accurately detect when an anomaly occurs?
LSCALE: Latent Space Clustering-Based Active Learning for Node Classification
We argue that the representation power in unlabelled nodes can be useful for active learning and for further improving performance of active learning for node classification.
Origin-Aware Next Destination Recommendation with Personalized Preference Attention
Next destination recommendation is an important task in the transportation domain of taxi and ride-hailing services, where users are recommended with personalized destinations given their current origin location.
Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach
This allows us to detect sudden changes in the importance of any node.
Autonomous Graph Mining Algorithm Search with Best Speed/Accuracy Trade-off
We first define a unified framework UNIFIEDGM that integrates various message-passing based graph algorithms, ranging from conventional algorithms like PageRank to graph neural networks.
STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation
Next Point-of-Interest (POI) recommendation is a longstanding problem across the domains of Location-Based Social Networks (LBSN) and transportation.
SHADOWCAST: Controllable Graph Generation with Explainability
We introduce the problem of explaining graph generation, formulated as controlling the generative process to produce desired graphs with explainable structures.
GraphCrop: Subgraph Cropping for Graph Classification
We present a new method to regularize graph neural networks (GNNs) for better generalization in graph classification.
Real-Time Anomaly Detection in Edge Streams
Given a stream of graph edges from a dynamic graph, how can we assign anomaly scores to edges in an online manner, for the purpose of detecting unusual behavior, using constant time and memory?
ExGAN: Adversarial Generation of Extreme Samples
Hence, in this work, we propose ExGAN, a GAN-based approach to generate realistic and extreme samples.
MSTREAM: Fast Anomaly Detection in Multi-Aspect Streams
Given a stream of entries in a multi-aspect data setting i. e., entries having multiple dimensions, how can we detect anomalous activities in an unsupervised manner?
Ranked #1 on
Intrusion Detection
on CIC-DDoS
Understanding and Resolving Performance Degradation in Graph Convolutional Networks
In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.
Structural Patterns and Generative Models of Real-world Hypergraphs
Graphs have been utilized as a powerful tool to model pairwise relationships between people or objects.
Social and Information Networks Physics and Society
SHADOWCAST: Controllable Graph Generation
Given an observed graph and some user-specified Markov model parameters, ${\rm S{\small HADOW}C{\small AST}}$ controls the conditions to generate desired graphs.
MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams
Given a stream of graph edges from a dynamic graph, how can we assign anomaly scores to edges in an online manner, for the purpose of detecting unusual behavior, using constant time and memory?
Ranked #1 on
Anomaly Detection in Edge Streams
on Darpa
Identifying through Flows for Recovering Latent Representations
Yet, most deep generative models do not address the question of identifiability, and thus fail to deliver on the promise of the recovery of the true latent sources that generate the observations.
Out-of-Core and Distributed Algorithms for Dense Subtensor Mining
Can we detect it when data are too large to fit in memory or even on a disk?
Databases Distributed, Parallel, and Cluster Computing Social and Information Networks H.2.8
HoloScope: Topology-and-Spike Aware Fraud Detection
Hence, we propose HoloScope, which uses information from graph topology and temporal spikes to more accurately detect groups of fraudulent users.
Social and Information Networks
FairJudge: Trustworthy User Prediction in Rating Platforms
We propose three metrics: (i) the fairness of a user that quantifies how trustworthy the user is in rating the products, (ii) the reliability of a rating that measures how reliable the rating is, and (iii) the goodness of a product that measures the quality of the product.
BIRDNEST: Bayesian Inference for Ratings-Fraud Detection
To combine these 2 approaches, we formulate our Bayesian Inference for Rating Data (BIRD) model, a flexible Bayesian model of user rating behavior.
