Search Results for author:
Found 206 papers, 76 papers with code
ASCM: An Answer Space Clustered Prompting Method without Answer Engineering
We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models.
Knowledge Transfer between Structured and Unstructured Sources for Complex Question Answering
More fine-grained analyses on transfer behaviors reveal the types of transferred knowledge and transfer patterns.
Deep Streaming Label Learning
In order to fill in these research gaps, we propose a novel deep neural network (DNN) based framework, Deep Streaming Label Learning (DSLL), to classify instances with newly emerged labels effectively.
Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion Models
We introduce a likelihood-guided noise refinement mechanism that derives a closed-form approximation of the likelihood score, simplifying score estimation and avoiding expensive gradient computations.
Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems
To address these challenges, this paper proposes a novel graph backdoor attack method that aims to enhance the exposure of target items to the target user in a covert manner, without affecting other unrelated nodes.
Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
However, transferring knowledge from single-arm datasets or pre-trained VLA models often fails to generalize effectively, primarily due to the scarcity of bimanual data and the fundamental differences between single-arm and bimanual manipulation.
The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
The top-performing model(s) within that cluster are selected to generate the response using the Self-Consistency or its multi-model variant.
Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity
To address these issues, we propose a novel method called CausalEPP (Causal Intervention on Evolving Personal Popularity) for taming recommendation bias, which accounts for the evolving personal popularity of users.
Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General Reasoning
Our approach leverages Large Language Models (LLMs) to adapt game code, enabling automatic acquisition of reasoning processes and results through code execution.
SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs
Source detection on graphs has demonstrated high efficacy in identifying rumor origins.
HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion
Hypergraphs offer superior modeling capabilities for social networks, particularly in capturing group phenomena that extend beyond pairwise interactions in rumor propagation.
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models
The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever.
A 3D pocket-aware and evolutionary conserved interaction guided diffusion model for molecular optimization
Generating molecules that bind to specific protein targets via diffusion models has shown good promise for structure-based drug design and molecule optimization.
Beyond the Tragedy of the Commons: Building A Reputation System for Generative Multi-agent Systems
The tragedy of the commons, where individual self-interest leads to collectively disastrous outcomes, is a pervasive challenge in human society.
On the Robustness of GUI Grounding Models Against Image Attacks
Graphical User Interface (GUI) grounding models are crucial for enabling intelligent agents to understand and interact with complex visual interfaces.
Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
In this paper, we introduce Feature4X, a universal framework designed to extend any functionality from 2D vision foundation model into the 4D realm, using only monocular video input, which is widely available from user-generated content.
Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling
To answer this, we explore the role of negative nodes in the commonly used InfoNCE loss for GCL and observe that: (1) Counterintuitively, a large number of negative nodes can actually hinder the model's ability to distinguish nodes with different semantics.
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts
Additionally, the 8B model can surpass GPT-4o up to 43. 88% with an average of 11. 00%.
Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances
Autonomous Driving Systems (ADSs) are revolutionizing transportation by reducing human intervention, improving operational efficiency, and enhancing safety.
If Multi-Agent Debate is the Answer, What is the Question?
Multi-agent debate (MAD) has emerged as a promising approach to enhance the factual accuracy and reasoning quality of large language models (LLMs) by engaging multiple agents in iterative discussions during inference.
SMI: An Information-Theoretic Metric for Predicting Model Knowledge Solely from Pre-Training Signals
The GPT-4 technical report highlights the possibility of predicting model performance on downstream tasks using only pre-training signals, though detailed methodologies are absent.
PQD: Post-training Quantization for Efficient Diffusion Models
Experimental results show that our proposed method is able to directly quantize full-precision diffusion models into 8-bit or 4-bit models while maintaining comparable performance in a training-free manner, achieving a few FID change on ImageNet for unconditional image generation.
Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
Specifically, by appropriately defining \emph{structure noise} and \emph{feature noise} in graphs, we show that graph attention mechanisms can enhance classification performance when structure noise exceeds feature noise.
EquiFlow: Equivariant Conditional Flow Matching with Optimal Transport for 3D Molecular Conformation Prediction
EquiFlow uniquely applies conditional flow matching in molecular 3D conformation prediction, leveraging simulation-free training to address slow training speeds.
From Exploration to Revelation: Detecting Dark Patterns in Mobile Apps
While some studies targeted at automated detection, they are constrained to static patterns and still necessitate manual app exploration.
Less is More: Efficient Model Merging with Binary Task Switch
However, existing methods face challenges of redundant parameter conflicts and the excessive storage burden of parameters.
IterIS: Iterative Inference-Solving Alignment for LoRA Merging
Prior works on LoRA merging primarily frame it as an optimization problem, yet these approaches face several limitations, including the rough assumption about input features utilized in optimization, massive sample requirements, and the unbalanced optimization objective.
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models
To further lower costs and achieve alignment without any expensive tuning or annotations, we introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (DRPO).
Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction
Subgraph-based methods have proven to be effective and interpretable in predicting drug-drug interactions (DDIs), which are essential for medical practice and drug development.
Prediction by Machine Learning Analysis of Genomic Data Phenotypic Frost Tolerance in Perccottus glenii
Analysis of the genome sequence of Perccottus glenii, the only fish known to possess freeze tolerance, holds significant importance for understanding how organisms adapt to extreme environments, Traditional biological analysis methods are time-consuming and have limited accuracy, To address these issues, we will employ machine learning techniques to analyze the gene sequences of Perccottus glenii, with Neodontobutis hainanens as a comparative group, Firstly, we have proposed five gene sequence vectorization methods and a method for handling ultra-long gene sequences, We conducted a comparative study on the three vectorization methods: ordinal encoding, One-Hot encoding, and K-mer encoding, to identify the optimal encoding method, Secondly, we constructed four classification models: Random Forest, LightGBM, XGBoost, and Decision Tree, The dataset used by these classification models was extracted from the National Center for Biotechnology Information database, and we vectorized the sequence matrices using the optimal encoding method, K-mer, The Random Forest model, which is the optimal model, achieved a classification accuracy of up to 99, 98 , Lastly, we utilized SHAP values to conduct an interpretable analysis of the optimal classification model, Through ten-fold cross-validation and the AUC metric, we identified the top 10 features that contribute the most to the model's classification accuracy, This demonstrates that machine learning methods can effectively replace traditional manual analysis in identifying genes associated with the freeze tolerance phenotype in Perccottus glenii.
Test-Time Intensity Consistency Adaptation for Shadow Detection
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context.
Diffusion Models in 3D Vision: A Survey
In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging.
Combing Text-based and Drag-based Editing for Precise and Flexible Image Editing
To address these issues, we proposed \textbf{CLIPDrag}, a novel image editing method that is the first to combine text and drag signals for precise and ambiguity-free manipulations on diffusion models.
Event-Customized Image Generation
To extend customized image generation to more complex scenes for general real-world applications, we propose a new task: event-customized image generation.
Task-agnostic Pre-training and Task-guided Fine-tuning for Versatile Diffusion Planner
Then for downstream tasks, we adopt RL-based fine-tuning with task-specific rewards to quickly refine the diffusion planner, which aims to generate action sequences with higher task-specific returns.
Overcoming the Machine Penalty with Imperfectly Fair AI Agents
Despite rapid technological progress, effective human-machine cooperation remains a significant challenge.
CUS3D :CLIP-based Unsupervised 3D Segmentation via Object-level Denoise
To ease the difficulty of acquiring annotation labels in 3D data, a common method is using unsupervised and open-vocabulary semantic segmentation, which leverage 2D CLIP semantic knowledge.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
Application Research On Real-Time Perception Of Device Performance Status
In order to accurately identify the performance status of mobile devices and finely adjust the user experience, a real-time performance perception evaluation method based on TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) combined with entropy weighting method and time series model construction was studied.
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
Virtual Screening is an essential technique in the early phases of drug discovery, aimed at identifying promising drug candidates from vast molecular libraries.
LalaEval: A Holistic Human Evaluation Framework for Domain-Specific Large Language Models
This paper introduces LalaEval, a holistic framework designed for the human evaluation of domain-specific large language models (LLMs).
Understanding Literary Texts by LLMs: A Case Study of Ancient Chinese Poetry
Additionally, evaluating literary works is often complex and hard to fully quantify, which directly hinders the further development of AI creation.
Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation
Its objective is to extract knowledge from extensive pre-training data and fine-tune the model for downstream tasks.
Analytical and Empirical Study of Herding Effects in Recommendation Systems
We also study the speed of convergence numerically and reveal trade-offs in selecting rating aggregation rules and review selection mechanisms.
scASDC: Attention Enhanced Structural Deep Clustering for Single-cell RNA-seq Data
Single-cell RNA sequencing (scRNA-seq) data analysis is pivotal for understanding cellular heterogeneity.
Cross-Scan Mamba with Masked Training for Robust Spectral Imaging
Current CNN-based methods are limited in modeling long-range dependencies, while Transformer-based models face high computational complexity.
Pavement Fatigue Crack Detection and Severity Classification Based on Convolutional Neural Network
The first objective of the proposed neural network is to classify presence of fatigue cracking based on pavement surface images.
Foundations and Frontiers of Graph Learning Theory
Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures.
Probing many-body Bell correlation depth with superconducting qubits
As an illustrating example, we variationally prepare the low-energy state of a two-dimensional honeycomb model with 73 qubits and certify its Bell correlations by measuring an energy that surpasses the corresponding classical bound with up to 48 standard deviations.
Uni-Mol2: Exploring Molecular Pretraining Model at Scale
In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences.
Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
Our findings highlight the critical role of modularity, the applicability of Self-MoE to multiple base LLMs, and the potential of self-improvement in achieving efficient, scalable, and adaptable systems.
FreeTuner: Any Subject in Any Style with Training-free Diffusion
With the advance of diffusion models, various personalized image generation methods have been proposed.
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
In this paper, we propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.
Learning Partially Aligned Item Representation for Cross-Domain Sequential Recommendation
Cross-domain sequential recommendation (CDSR) aims to uncover and transfer users' sequential preferences across multiple recommendation domains.
MaskFuser: Masked Fusion of Joint Multi-Modal Tokenization for End-to-End Autonomous Driving
The masked training enhances the fusion representation by reconstruction on masked tokens.
Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning
To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning.
Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
In this paper, we propose a novel representation-based approach to measure the domain gap, where the representation is learned through a contrastive objective by sampling transitions from different domains.
A Survey on Deep Active Learning: Recent Advances and New Frontiers
Active learning seeks to achieve strong performance with fewer training samples.
Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
We further provide theoretical analysis, which shows that the optimality gap of our method is only related to the expected data coverage of the shared dataset, thus resolving the distribution shift issue in data sharing.
Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning
Finally, we extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.
A General Black-box Adversarial Attack on Graph-based Fake News Detectors
Specifically, as sharing is an important social interaction for GNN-based fake news detectors to construct the graph, we simulate sharing behaviors to fool the detectors.
Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
Offline Reinforcement Learning (RL) faces distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions.
LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
(2) We develop LLM Reasoners, a library for standardized modular implementation of existing and new reasoning algorithms, under a unified formulation of the search, reward, and world model components.
AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement
Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool.
Graph Regularized NMF with L20-norm for Unsupervised Feature Learning
Nonnegative Matrix Factorization (NMF) is a widely applied technique in the fields of machine learning and data mining.
Emergence of Social Norms in Generative Agent Societies: Principles and Architecture
Our experiments deployed in the Smallville sandbox game environment demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs.
GIN-SD: Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion
In this paper, we address a more challenging task, rumor source detection with incomplete user data, and propose a novel framework, i. e., Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion (GIN-SD), to tackle this challenge.
Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas
Third, we review the emergent field of leveraging AI agents to enhance cooperation among humans.
Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark
Although previous counterfactual QA benchmarks can separate the internal memory of LLMs, they focus solely on final QA performance, which is insufficient for reporting LLMs' real reasoning abilities.
Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks
While such methods could improve GNN predictions, they usually don't perform well on explanations.
Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning
Compared to training on the entire augmented dataset, our ECL strategy can further enhance VQA models' performance with fewer training samples.
Diffusion-based Data Augmentation for Object Counting Problems
Our proposed smoothed density map input for ControlNet significantly improves ControlNet's performance in generating crowds in the correct locations.
Community Detection in the Multi-View Stochastic Block Model
This paper considers the problem of community detection on multiple potentially correlated graphs from an information-theoretical perspective.
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
To the best of our knowledge, SKR is the first attempt to address the time-consuming nature of data generation for learning neural operators.
Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms
Theoretical analyses show that our algorithm succeeds with high probability as long as the sample probability exceeds the aforementioned threshold, and this theoretical result is further validated by synthetic experiments.
Improving Graph Contrastive Learning via Adaptive Positive Sampling
Graph Contrastive Learning (GCL) a Self-Supervised Learning (SSL) architecture tailored for graphs has shown notable potential for mitigating label scarcity.
OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments
In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty.
Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity
Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions.
Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation
In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels.
GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with Masking
With the rise of social media, the spread of fake news has become a significant concern, potentially misleading public perceptions and impacting social stability.
MVDD: Multi-View Depth Diffusion Models
State-of-the-art results from extensive experiments demonstrate MVDD's excellent ability in 3D shape generation, depth completion, and its potential as a 3D prior for downstream tasks.
Control of the Power Flows of a Stochastic Power System
How to determine the vector of power supplies of a stochastic power system for the next short horizon, such that the probability is less than a prespecified value that any phase-angle difference of a power line of the power network exits from a safe set?
DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism
The denoising process involves the explicit predictions of edit operations and corresponding content words, refining reference captions through iterative step-wise editing.
Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
While this phenomenon has been overlooked in previous work, we propose a novel and extensible framework, called Octavius, for comprehensive studies and experimentation on multimodal learning with Multimodal Large Language Models (MLLMs).
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task.
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL).
Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness
Experimental results illustrate the superiority of RO2O in facilitating stable offline-to-online learning and achieving significant improvement with limited online interactions.
Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesis
Single-step retrosynthesis (SSR) in organic chemistry is increasingly benefiting from deep learning (DL) techniques in computer-aided synthesis design.
Ranked #1 on
Single-step retrosynthesis
on USPTO-50k
LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data
We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.
Least Squares Maximum and Weighted Generalization-Memorization Machines
Furthermore, we propose some different memory impact functions for the MIMM and WIMM.
FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings
Instead, we view this as a multimodal task, using text as auxiliary information to facilitate the visual model's understanding of the logo.
IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse
Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task.
Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System
We introduce TacoBot, a user-centered task-oriented digital assistant designed to guide users through complex real-world tasks with multiple steps.
DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal
Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability.
Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model
Therefore, the attack models in existing MIAs are difficult to effectively train with the knowledge of the target model, resulting in sub-optimal attacks.
Sequential Attention Source Identification Based on Feature Representation
Snapshot observation based source localization has been widely studied due to its accessibility and low cost.
MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning
Fine-tuning large-scale pre-trained language models has been demonstrated effective for various natural language processing (NLP) tasks.
On the Value of Myopic Behavior in Policy Reuse
Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence.
Reasoning with Language Model is Planning with World Model
RAP on LLAMA-33B surpasses CoT on GPT-4 with 33% relative improvement in a plan generation setting.
Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID
To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters.
ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection
Then both the initial and edited embeddings are projected back (deprojected) to the initial latent space as residuals to modify the input latent vectors by subtraction and addition, representing old status removal and new status addition.
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to solving complex problems.
Behavior Contrastive Learning for Unsupervised Skill Discovery
Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective.
Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning
Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios.
Delving into Shape-aware Zero-shot Semantic Segmentation
Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.
HPN: Personalized Federated Hyperparameter Optimization
The client encoding is calculated with a random projection-based procedure to protect each client's privacy.
GPT is becoming a Turing machine: Here are some ways to program it
We demonstrate that, through appropriate prompting, GPT-3 family of models can be triggered to perform iterative behaviours necessary to execute (rather than just write or recall) programs that involve loops, including several popular algorithms found in computer science curricula or software developer interviews.
LON-GNN: Spectral GNNs with Learnable Orthonormal Basis
In recent years, a plethora of spectral graph neural networks (GNN) methods have utilized polynomial basis with learnable coefficients to achieve top-tier performances on many node-level tasks.
Learning Combinatorial Prompts for Universal Controllable Image Captioning
To this end, we propose a novel prompt-based framework for CIC by learning Combinatorial Prompts, dubbed as ComPro.
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning
Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks.
Exit options sustain altruistic punishment and decrease the second-order free-riders, but it is not a panacea
Altruistic punishment, where individuals incur personal costs to punish others who have harmed third parties, presents an evolutionary conundrum as it undermines individual fitness.
Hard Sample Aware Network for Contrastive Deep Graph Clustering
Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones.
ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction
One school of thought is to encode a latent vector for each point (point latents).
Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification
In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'.
BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules.
Search to Pass Messages for Temporal Knowledge Graph Completion
In particular, we develop a generalized framework to explore topological and temporal information in TKGs.
Ranked #1 on
Link Prediction
on GDELT
Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding
Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks.
A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning
Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains.
ThinkSum: Probabilistic reasoning over sets using large language models
Our results suggest that because the probabilistic inference in ThinkSum is performed outside of calls to the LLM, ThinkSum is less sensitive to prompt design, yields more interpretable predictions, and can be flexibly combined with latent variable models to extract structured knowledge from LLMs.
Cross Task Neural Architecture Search for EEG Signal Classifications
Recently, various neural network approaches have been proposed to improve the accuracy of EEG signal recognition.
Hiding Visual Information via Obfuscating Adversarial Perturbations
Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection.
Compressed Sensing Based RFI Mitigation and Restoration for Pulsar Signals
In pulsar signal processing, two primary difficulties are (1) radio-frequency interference (RFI) mitigation and (2) information loss due to preprocessing and mitigation itself.
A Game-Theoretic Perspective of Generalization in Reinforcement Learning
However, there is not a unified formulation of the various schemes, as well as the comprehensive comparisons of methods across different schemes.
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning
Continual learning is a learning paradigm that learns tasks sequentially with resources constraints, in which the key challenge is stability-plasticity dilemma, i. e., it is uneasy to simultaneously have the stability to prevent catastrophic forgetting of old tasks and the plasticity to learn new tasks well.
Online Continual Learning with Contrastive Vision Transformer
Based on the learnable focuses, we design a focal contrastive loss to rebalance contrastive learning between new and past classes and consolidate previously learned representations.
Explicit Image Caption Editing
Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption.
Bootstrapping a User-Centered Task-Oriented Dialogue System
We present TacoBot, a task-oriented dialogue system built for the inaugural Alexa Prize TaskBot Challenge, which assists users in completing multi-step cooking and home improvement tasks.
Generalization-Memorization Machines
Under this mechanism, error-based learning machines improve their memorization abilities of training data without over-fitting.
Modern Question Answering Datasets and Benchmarks: A Survey
Question Answering (QA) is one of the most important natural language processing (NLP) tasks.
FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization
Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting.
A Benchmark for Federated Hetero-Task Learning
To investigate the heterogeneity in federated learning in real-world scenarios, we generalize the classic federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants in federated learning in terms of both data distribution and learning tasks.
EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
Despite their extraordinary predictive accuracy, existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs, rendering these models vulnerable to graph structural attacks and with limited capacity in generalizing to graphs of varied homophily levels.
D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat
In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria.
PrEF: Percolation-based Evolutionary Framework for the diffusion-source-localization problem in large networks
We assume that the state of a number of nodes in a network could be investigated if necessary, and study what configuration of those nodes could facilitate a better solution for the diffusion-source-localization (DSL) problem.
Towards Fine-grained Causal Reasoning and QA
Understanding causality is key to the success of NLP applications, especially in high-stakes domains.
FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning
The incredible development of federated learning (FL) has benefited various tasks in the domains of computer vision and natural language processing, and the existing frameworks such as TFF and FATE has made the deployment easy in real-world applications.
FederatedScope: A Flexible Federated Learning Platform for Heterogeneity
Although remarkable progress has been made by existing federated learning (FL) platforms to provide infrastructures for development, these platforms may not well tackle the challenges brought by various types of heterogeneity, including the heterogeneity in participants' local data, resources, behaviors and learning goals.
PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations
In online adaptation phase, with the environment context inferred from few experiences collected in new environments, the policy is optimized by gradient ascent with respect to the PDVF.
Experimental quantum adversarial learning with programmable superconducting qubits
Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework
To break this curse, we propose a unified agent permutation framework that exploits the permutation invariance (PI) and permutation equivariance (PE) inductive biases to reduce the multiagent state space.
Regularized Bilinear Discriminant Analysis for Multivariate Time Series Data
To address the two problems, we propose RBLDA for MTS data classification, where each of the two within-class matrices is regularized via one parameter.
Adversarial Attacks and Defense Methods for Power Quality Recognition
To this end, we first propose a signal-specific method and a universal signal-agnostic method to attack power systems using generated adversarial examples.
Compactness Score: A Fast Filter Method for Unsupervised Feature Selection
For feature engineering, feature selection seems to be an important research content in which is anticipated to select "excellent" features from candidate ones.
MR-SVS: Singing Voice Synthesis with Multi-Reference Encoder
However, they face several challenges: 1) the fixed-size speaker embedding is not powerful enough to capture full details of the target timbre; 2) single reference audio does not contain sufficient timbre information of the target speaker; 3) the pitch inconsistency between different speakers also leads to a degradation in the generated voice.
Synthetic Generation of Face Videos With Plethysmograph Physiology
Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement.
Continual Learning With Lifelong Vision Transformer
Continual learning methods aim at training a neural network from sequential data with streaming labels, relieving catastrophic forgetting.
ED2: Environment Dynamics Decomposition World Models for Continuous Control
Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence of model prediction error.
Understanding the Dynamics of DNNs Using Graph Modularity
Specifically, we model the process of class separation of intermediate representations in pre-trained DNNs as the evolution of communities in dynamic graphs.
Graph-Based Similarity of Neural Network Representations
Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning.
Coherence boosting: When your pretrained language model is not paying enough attention
Long-range semantic coherence remains a challenge in automatic language generation and understanding.
Coarformer: Transformer for large graph via graph coarsening
We get rid of these obstacles by exploiting the complementary natures of GNN and Transformer, and trade the fine-grained long-range information for the efficiency of Transformer.
iFlood: A Stable and Effective Regularizer
However, our further studies uncover that the design of the loss function of Flooding can lead to a discrepancy between its objective and implementation, and cause the instability issue.
Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
In addition to algorithmic analysis, we provide a comprehensive and unified empirical comparison of different exploration methods for DRL on a set of commonly used benchmarks.
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI.
N24News: A New Dataset for Multimodal News Classification
Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification.
Ranked #1 on
News Classification
on N15News
Synchronization of Power Systems under Stochastic Disturbances
The synchronization of power generators is an important condition for the proper functioning of a power system, in which the fluctuations in frequency and the phase angle differences between the generators are sufficiently small when subjected to stochastic disturbances.
MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection
This paper describes the system submitted to SemEval 2021 Task 5: Toxic Spans Detection.
Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation
Camera-based remote photoplethysmography (rPPG) provides a non-contact way to measure physiological signals (e. g., heart rate) using facial videos.
Chinese Sentences Similarity via Cross-Attention Based Siamese Network
Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages.
Fuzzy Discriminant Clustering with Fuzzy Pairwise Constraints
In semi-supervised fuzzy clustering, this paper extends the traditional pairwise constraint (i. e., must-link or cannot-link) to fuzzy pairwise constraint.
Equilibrium and Socially optimal of a double-sided queueing system with two-mass point matching time
The numerical scenarios illustrate the influence of parameters on the equilibrium strategy and socially optimal strategy under two information levels.
Probability 60K25, 91B50, 91A35
Ensemble and Random Collaborative Representation-Based Anomaly Detector for Hyperspectral Imagery
To alleviate this problem, we proposed a novel ensemble and random collaborative representation-based detector (ERCRD) for HAD, which comprises two closely related stages.
Semantic Inference Network for Few-shot Streaming Label Learning
In this work, we formulate and study few-shot streaming label learning (FSLL), which models emerging new labels with only a few annotated examples by utilizing the knowledge learned from past labels.
ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries
This work proposes a generic evaluation metric ROBY, a novel attack-independent robustness measure based on the model's decision boundaries.
EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation
As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment.
Diversify Question Generation with Continuous Content Selectors and Question Type Modeling
However, question generation is actually a one-to-many problem, as it is possible to raise questions with different focuses on contexts and various means of expression.
Method and Dataset Entity Mining in Scientific Literature: A CNN + Bi-LSTM Model with Self-attention
We finally apply our model on PAKDD papers published from 2009-2019 to mine insightful results from scientific papers published in a longer time span.
Exercise Hierarchical Feature Enhanced Knowledge Tracing
Knowledge tracing is a fundamental task in the computer-aid educational system.
Exploring Common and Individual Characteristics of Students via Matrix Recovering
We assume that the characteristics matrix of students' is composed of two parts: one is a low-rank matrix representing the common characteristics of students; the other is a sparse matrix representing individual characteristics of students.
Unseen Target Stance Detection with Adversarial Domain Generalization
Although stance detection has made great progress in the past few years, it is still facing the problem of unseen targets.
Cue-word Driven Neural Response Generation with a Shrinking Vocabulary
Open-domain response generation is the task of generating sensible and informative re-sponses to the source sentence.
FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data
Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.
HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing
To solve the above problems, we propose a hierarchical graph knowledge tracing model called HGKT to explore the latent hierarchical relations between exercises.
Training Noise-Robust Deep Neural Networks via Meta-Learning
Label noise may significantly degrade the performance of Deep Neural Networks (DNNs).
Rationalizing Medical Relation Prediction from Corpus-level Statistics
Nowadays, the interpretability of machine learning models is becoming increasingly important, especially in the medical domain.
A Semi-supervised Graph Attentive Network for Financial Fraud Detection
Additionally, among the network, only very few of the users are labelled, which also poses a great challenge for only utilizing labeled data to achieve a satisfied performance on fraud detection.
Tree++: Truncated Tree Based Graph Kernels
At the heart of Tree++ is a graph kernel called the path-pattern graph kernel.
Multiple Flat Projections for Cross-manifold Clustering
In this paper, we propose a Multiple Flat Projections Clustering (MFPC) to deal with cross-manifold clustering problems.
Texture Classification using Block Intensity and Gradient Difference (BIGD) Descriptor
In this paper, we present an efficient and distinctive local descriptor, namely block intensity and gradient difference (BIGD).
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.
Learning to Answer Subjective, Specific Product-Related Queries using Customer Reviews by Adversarial Domain Adaptation
Online customer reviews on large-scale e-commerce websites, represent a rich and varied source of opinion data, often providing subjective qualitative assessments of product usage that can help potential customers to discover features that meet their personal needs and preferences.
A Distributed Fair Machine Learning Framework with Private Demographic Data Protection
In this paper, we propose a distributed fair learning framework for protecting the privacy of demographic data.
SurfCon: Synonym Discovery on Privacy-Aware Clinical Data
To solve the problem, we propose a new framework SurfCon that leverages two important types of information in the privacy-aware clinical data, i. e., the surface form information, and the global context information for synonym discovery.
Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
Our experimental results demonstrate that the recent graph embedding methods achieve promising results and deserve more attention in the future biomedical graph analysis.
Fisher-Bures Adversary Graph Convolutional Networks
We try to minimize the loss wrt the perturbed $G+\Delta{G}$ while making $\Delta{G}$ to be effective in terms of the Fisher information of the neural network.
Artificial Intelligence for Prosthetics - challenge solutions
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
Characterization of migrated seismic volumes using texture attributes: a comparative study
It is our hope that this comparative study will help acquaint the seismic interpretation community with the many available powerful image texture analysis techniques, providing more alternative attributes for their seismic exploration.
A general model for plane-based clustering with loss function
In this paper, we propose a general model for plane-based clustering.
A comparative study of texture attributes for characterizing subsurface structures in seismic volumes
We focus on spatial attributes in this study and examine them in a new application for seismic interpretation, i. e., seismic volume labeling.
Ramp-based Twin Support Vector Clustering
Traditional plane-based clustering methods measure the cost of within-cluster and between-cluster by quadratic, linear or some other unbounded functions, which may amplify the impact of cost.
Robust Bhattacharyya bound linear discriminant analysis through adaptive algorithm
In this paper, we propose a novel linear discriminant analysis criterion via the Bhattacharyya error bound estimation based on a novel L1-norm (L1BLDA) and L2-norm (L2BLDA).
Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension
While sophisticated neural-based techniques have been developed in reading comprehension, most approaches model the answer in an independent manner, ignoring its relations with other answer candidates.
A Many-Objective Evolutionary Algorithm With Two Interacting Processes: Cascade Clustering and Reference Point Incremental Learning
This paper proposes a many-objective optimization algorithm with two interacting processes: cascade clustering and reference point incremental learning (CLIA).
Generalized two-dimensional linear discriminant analysis with regularization
However, 2DLDA may encounter the singularity issue theoretically and the sensitivity to outliers.
On the Effectiveness of Least Squares Generative Adversarial Networks
To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss for both the discriminator and the generator.
Insensitive Stochastic Gradient Twin Support Vector Machine for Large Scale Problems
In this paper, stochastic gradient descent algorithm is investigated to twin support vector machines for classification.
Least Squares Generative Adversarial Networks
To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator.
