Search Results for author:
Found 86 papers, 27 papers with code
Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration
Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design.
CD-Lamba: Boosting Remote Sensing Change Detection via a Cross-Temporal Locally Adaptive State Space Model
However, existing remote sensing change detection (RSCD) approaches based on Mamba frequently struggle to effectively perceive the inherent locality of change regions as they direct flatten and scan RS images (i. e., the features of the same region of changes are not distributed continuously within the sequence but are mixed with features from other regions throughout the sequence).
TopoLa: A Universal Framework to Enhance Cell Representations for Single-cell and Spatial Omics through Topology-encoded Latent Hyperbolic Geometry
Recent advances in cellular research demonstrate that scRNA-seq characterizes cellular heterogeneity, while spatial transcriptomics reveals the spatial distribution of gene expression.
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
ReARTeR addresses three core challenges: (1) misalignment between PRM and PEM, tackled through off-policy preference learning; (2) bias in PRM training data, mitigated by balanced annotation methods and stronger annotations for challenging examples; and (3) early-step bias in PRM, resolved through a temporal-difference-based look-ahead search strategy.
Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models
We introduce a new concept, "Integrating Recommendation Systems as a New Language in Large Models" (RSLLM), which combines the strengths of traditional recommenders and LLMs.
Trigger$^3$: Refining Query Correction via Adaptive Model Selector
To tackle these, we propose Trigger$^3$, a large-small model collaboration framework that integrates the traditional correction model and LLM for query correction, capable of adaptively choosing the appropriate correction method based on the query and the correction results from the traditional correction model and LLM.
Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
From the spatial data management perspective, we present a novel Transformer framework called PatchSTG to efficiently and dynamically model spatial dependencies for large-scale traffic forecasting with interpretability and fidelity.
Ranked #1 on
Traffic Prediction
on LargeST
MILLION: A General Multi-Objective Framework with Controllable Risk for Portfolio Management
Subsequently, in the risk control phase, we propose two methods, i. e., portfolio interpolation and portfolio improvement, to achieve fine-grained risk control and fast risk adaption to a user-specified risk level.
Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search
To achieve this, we propose an Data-Aware Distance Estimation approach, called DADE, which approximates the exact distance in a lower-dimensional space.
On-device Content-based Recommendation with Single-shot Embedding Pruning: A Cooperative Game Perspective
To address the inherently high computation costs of Shapley values, we propose an efficient and unbiased method to estimate Shapley values of a CRS's embedding parameters.
KuaiFormer: Transformer-Based Retrieval at Kuaishou
In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules.
CDXFormer: Boosting Remote Sensing Change Detection with Extended Long Short-Term Memory
In complex scenes and varied conditions, effectively integrating spatial-temporal context is crucial for accurately identifying changes.
RecFlow: An Industrial Full Flow Recommendation Dataset
Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users.
LargePiG: Your Large Language Model is Secretly a Pointer Generator
To validate the effectiveness of LargePiG, we constructed two datasets for assessing the hallucination problems in query generation, covering both document and video scenarios.
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
We discover hallucinations occur when the Knowledge FFNs in LLMs overemphasize parametric knowledge in the residual stream, while Copying Heads fail to effectively retain or integrate external knowledge from retrieved content.
Environment Scan of Generative AI Infrastructure for Clinical and Translational Science
This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the Clinical and Translational Science Award (CTSA) Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States.
Ascend HiFloat8 Format for Deep Learning
This preliminary white paper proposes a novel 8-bit floating-point data format HiFloat8 (abbreviated as HiF8) for deep learning.
Beyond Relevance: Improving User Engagement by Personalization for Short-Video Search
Personalized search has been extensively studied in various applications, including web search, e-commerce, social networks, etc.
DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models
Nevertheless, a straightforward combination of SR and DM leads to sub-optimal performance due to discrepancies in learning objectives (recommendation vs. noise reconstruction) and the respective learning spaces (non-stationary vs. stationary).
TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou
The significance of modeling long-term user interests for CTR prediction tasks in large-scale recommendation systems is progressively gaining attention among researchers and practitioners.
MaskVD: Region Masking for Efficient Video Object Detection
Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs).
Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction
This oversight can lead to misinterpretations of speakers' intentions, resulting in inconsistent or even contradictory responses within dialogues.
Full Stage Learning to Rank: A Unified Framework for Multi-Stage Systems
To address this issue, we propose an improved ranking principle for multi-stage systems, namely the Generalized Probability Ranking Principle (GPRP), to emphasize both the selection bias in each stage of the system pipeline as well as the underlying interest of users.
LightTR: A Lightweight Framework for Federated Trajectory Recovery
Due to the limited acquisition capabilities of edge devices, a lot of trajectories are recorded at a low sampling rate, which may lead to the effectiveness drop of urban applications.
A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data
The widespread deployment of wireless and mobile devices results in a proliferation of spatio-temporal data that is used in applications, e. g., traffic prediction, human mobility mining, and air quality prediction, where spatio-temporal prediction is often essential to enable safety, predictability, or reliability.
Channel Estimation for AFDM With Superimposed Pilots
To improve the SE, we propose a novel AFDM channel estimation scheme by introducing the superimposed pilots in the DAFT domain.
UniSAR: Modeling User Transition Behaviors between Search and Recommendation
In this paper, we propose a framework named UniSAR that effectively models the different types of fine-grained behavior transitions for providing users a Unified Search And Recommendation service.
Poisoning Decentralized Collaborative Recommender System and Its Countermeasures
Knowledge sharing also opens a backdoor for model poisoning attacks, where adversaries disguise themselves as benign clients and disseminate polluted knowledge to achieve malicious goals like promoting an item's exposure rate.
Large Language Models Enhanced Collaborative Filtering
In this paper, drawing inspiration from the in-context learning and chain of thought reasoning in LLMs, we propose the Large Language Models enhanced Collaborative Filtering (LLM-CF) framework, which distils the world knowledge and reasoning capabilities of LLMs into collaborative filtering.
Deep Learning for Trajectory Data Management and Mining: A Survey and Beyond
In this paper, we present a comprehensive review of the development and recent advances in deep learning for trajectory computing (DL4Traj).
Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality
Then STRIPE incorporates separate spatial and temporal memory networks to capture and store prototypes of normal patterns, respectively.
Adaptive Hypergraph Network for Trust Prediction
In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations.
Physical Trajectory Inference Attack and Defense in Decentralized POI Recommendation
Empirical results demonstrate that PTIA poses a significant threat to users' historical trajectories.
Parameterized Decision-making with Multi-modal Perception for Autonomous Driving
Autonomous driving is an emerging technology that has advanced rapidly over the last decade.
Batch-Mix Negative Sampling for Learning Recommendation Retrievers
Recommendation retrievers commonly retrieve user potentially preferred items from numerous items, where the query and item representation are learned according to the dual encoders with the log-softmax loss.
Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning
To obtain efficiency and effectiveness, this paper introduces a generative retrieval framework, namely SEATER, which learns SEmAntic Tree-structured item identifiERs via contrastive learning.
To Predict or to Reject: Causal Effect Estimation with Uncertainty on Networked Data
Due to the imbalanced nature of networked observational data, the causal effect predictions for some individuals can severely violate the positivity/overlap assumption, rendering unreliable estimations.
Graph Contrastive Learning with Generative Adversarial Network
Specifically, we present GACN, a novel Generative Adversarial Contrastive learning Network for graph representation learning.
Graph Condensation for Inductive Node Representation Learning
To overcome this issue, we propose mapping-aware graph condensation (MCond), explicitly learning the one-to-many node mapping from original nodes to synthetic nodes to seamlessly integrate new nodes into the synthetic graph for inductive representation learning.
Personalized Elastic Embedding Learning for On-Device Recommendation
Given a memory budget, PEEL efficiently generates PEEs by selecting embedding blocks with the largest weights, making it adaptable to dynamic memory budgets on devices.
PANE-GNN: Unifying Positive and Negative Edges in Graph Neural Networks for Recommendation
Recommender systems play a crucial role in addressing the issue of information overload by delivering personalized recommendations to users.
Multi-behavior Self-supervised Learning for Recommendation
Secondly, existing methods utilizing self-supervised learning (SSL) to tackle the data sparsity neglect the serious optimization imbalance between the SSL task and the target task.
Instant Representation Learning for Recommendation over Large Dynamic Graphs
Furthermore, the Neighborhood Disturbance existing in dynamic graphs deteriorates the performance of neighbor-aggregation based graph models.
Self-Supervised Multi-Modal Sequential Recommendation
To address this issue, we propose a dual-tower retrieval architecture for sequence recommendation.
WizardLM: Empowering Large Language Models to Follow Complex Instructions
In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans.
Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation
In light of this, We propose a novel on-device POI recommendation framework, namely Model-Agnostic Collaborative learning for on-device POI recommendation (MAC), allowing users to customize their own model structures (e. g., dimension \& number of hidden layers).
Continuous Input Embedding Size Search For Recommender Systems
Latent factor models are the most popular backbones for today's recommender systems owing to their prominent performance.
A Pattern Discovery Approach to Multivariate Time Series Forecasting
To capture the temporal and multivariate correlations among subsequences, we design a pattern discovery model, that constructs correlations via diverse pattern functions.
Trajectory Flow Map: Graph-based Approach to Analysing Temporal Evolution of Aggregated Traffic Flows in Large-scale Urban Networks
First, we partition the entire network into a set of cells based on the spatial distribution of data points in individual trajectories, where the cells represent spatial regions between which aggregated traffic flows can be measured.
A Comparative Study on Unsupervised Anomaly Detection for Time Series: Experiments and Analysis
The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energy management, where anomaly detection is often essential to enable reliability and safety.
Uncertainty Quantification for Traffic Forecasting: A Unified Approach
To achieve this, we develop Deep Spatio-Temporal Uncertainty Quantification (DeepSTUQ), which can estimate both aleatoric and epistemic uncertainty.
Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss.
Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version
This is an extended version of "Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection", to appear in IEEE ICDE 2022.
DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks
Such heterogeneous network embedding (HNE) methods effectively harness the heterogeneity of small-scale HINs.
Boosting Contrastive Learning with Relation Knowledge Distillation
We delve into this problem and find that the lightweight model is prone to collapse in semantic space when simply performing instance-wise contrast.
Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version
To improve accuracy, the ensemble employs multiple basic outlier detection models built on convolutional sequence-to-sequence autoencoders that can capture temporal dependencies in time series.
Multimodal Dialogue Response Generation
In such a low-resource setting, we devise a novel conversational agent, Divter, in order to isolate parameters that depend on multimodal dialogues from the entire generation model.
Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
Variational AutoEncoder (VAE) has been extended as a representative nonlinear method for collaborative filtering.
Contrast R-CNN for Continual Learning in Object Detection
In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge.
HIFI: Anomaly Detection for Multivariate Time Series with High-order Feature Interactions
Monitoring complex systems results in massive multivariate time series data, and anomaly detection of these data is very important to maintain the normal operation of the systems.
Learning to Ask Appropriate Questions in Conversational Recommendation
Hence, the ability to generate suitable clarifying questions is the key to timely tracing users' dynamic preferences and achieving successful recommendations.
Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecasting
Long sequence time-series forecasting (LSTF) has become increasingly popular for its wide range of applications.
Hierarchical Hyperedge Embedding-based Representation Learning for Group Recommendation
However, the representation learning for a group is most complex beyond the fusion of group member representation, as the personal preferences and group preferences may be in different spaces.
Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure
Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.
Automated Creative Optimization for E-Commerce Advertising
However, interactions between creative elements may be more complex than the inner product, and the FM-estimated CTR may be of high variance due to limited feedback.
MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images
This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images.
Automated data extraction of bar chart raster images
Objective: To develop software utilizing optical character recognition toward the automatic extraction of data from bar charts for meta-analysis.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
Overcoming Data Sparsity in Group Recommendation
Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members.
SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply
In this setting, an assignment authority is to assign agents to requests such that the average idle time of the agents is minimized.
Databases Signal Processing
Stack-Sorting with Consecutive-Pattern-Avoiding Stacks
We introduce consecutive-pattern-avoiding stack-sorting maps $\text{SC}_\sigma$, which are natural generalizations of West's stack-sorting map $s$ and natural analogues of the classical-pattern-avoiding stack-sorting maps $s_\sigma$ recently introduced by Cerbai, Claesson, and Ferrari.
Combinatorics 05A05, 05A15, 37E15
Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem.
Locally Differentially Private (Contextual) Bandits Learning
We study locally differentially private (LDP) bandits learning in this paper.
(Locally) Differentially Private Combinatorial Semi-Bandits
In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting.
On Layer Normalization in the Transformer Architecture
This motivates us to remove the warm-up stage for the training of Pre-LN Transformers.
Combinatorial Semi-Bandit in the Non-Stationary Environment
In a special case where the reward function is linear and we have an exact oracle, we design a parameter-free algorithm that achieves nearly optimal regret both in the switching case and in the dynamic case without knowing the parameters in advance.
Bilinear Graph Neural Network with Neighbor Interactions
We term this framework as Bilinear Graph Neural Network (BGNN), which improves GNN representation ability with bilinear interactions between neighbor nodes.
The Strength of the Weakest Supervision: Topic Classification Using Class Labels
When developing topic classifiers for real-world applications, we begin by defining a set of meaningful topic labels.
Equipping Experts/Bandits with Long-term Memory
We propose the first reduction-based approach to obtaining long-term memory guarantees for online learning in the sense of Bousquet and Warmuth, 2002, by reducing the problem to achieving typical switching regret.
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Action recognition in videos has attracted a lot of attention in the past decade.
Efficient Online Portfolio with Logarithmic Regret
We study the decades-old problem of online portfolio management and propose the first algorithm with logarithmic regret that is not based on Cover's Universal Portfolio algorithm and admits much faster implementation.
RUM: network Representation learning throUgh Multi-level structural information preservation
We propose a novel network representations learning model framework called RUM (network Representation learning throUgh Multi-level structural information preservation).
End-to-end Learning for Short Text Expansion
A novel deep memory network is proposed to automatically find relevant information from a collection of longer documents and reformulate the short text through a gating mechanism.
Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints
This is the first algorithm-dependent result with reasonable dependence on aggregated step sizes for non-convex learning, and has important implications to statistical learning aspects of stochastic gradient methods in complicated models such as deep learning.
Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible
For learning with smooth generalized linear losses, we propose an approximate stochastic gradient oracle estimated from non-interactive LDP channel, using Chebyshev expansion.
Efficient Private ERM for Smooth Objectives
For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not only achieves nearly optimal utility, but also significantly improves the running time of previous state-of-the-art private optimization algorithms, for both $\epsilon$-DP and $(\epsilon, \delta)$-DP.
