Search Results for author:
Found 44 papers, 23 papers with code
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large language models (LLMs) with the analytical capabilities of spatio-temporal models for multi-task inference and execution.
Unlocking the Power of SAM 2 for Few-Shot Segmentation
A simple idea is to encode support foreground (FG) features as memory, with which query FG features are matched and fused.
SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning.
Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
However, a fundamental cross-modality gap between time series and LLMs exists, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series.
Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation
To address this problem, we introduce TimeKD, an efficient MTSF framework that leverages the calibrated language models and privileged knowledge distillation.
Knowledge Distillation
Multivariate Time Series Forecasting
+1
Generalization in Federated Learning: A Conditional Mutual Information Framework
Federated learning (FL) is a widely adopted privacy-preserving distributed learning framework, yet its generalization performance remains less explored compared to centralized learning.
HierPromptLM: A Pure PLM-based Framework for Representation Learning on Heterogeneous Text-rich Networks
However, this separation fails to capture the critical interactions between these two types of information within HTRNs.
Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
These items and item-related entities are often mentioned along the development of a dialog, leading to potential sequential dependencies among them.
Data Watermarking for Sequential Recommender Systems
In this work, we explore the problem of data watermarking for sequential recommender systems, where a watermark is embedded into the target dataset and can be detected in models trained on that dataset.
SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search
However, they face performance bottlenecks due to the random memory accesses caused by the searching process on the graph indices and the costs of computing exact distances to guide the searching process.
Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation
Furthermore, we introduce a Mixture-of-Experts (MoE) network in each attention head to disentangle various user preferences within each facet.
Hybrid Mamba for Few-Shot Segmentation
Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS.
Ranked #6 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search
In this paper, we introduce a new quantization method to address this limitation by extending RaBitQ.
iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search
In this study, instead of materializing a compressed index for every possible query range in preparation for querying, we materialize graph-based indexes, called elemental graphs, for a moderate number of ranges.
HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning
Based on this structure, we propose a novel Hierarchical Heterogeneous Graph Transformer (HHGT) model, which seamlessly integrates a Type-level Transformer for aggregating nodes of different types within each k-ring neighborhood, followed by a Ring-level Transformer for aggregating different k-ring neighborhoods in a hierarchical manner.
Watermarking Recommender Systems
To assess the efficacy of the watermark, the model is tasked with predicting the subsequent item given a truncated watermark sequence.
Eliminating Feature Ambiguity for Few-Shot Segmentation
Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features.
Ranked #7 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
As another key design, to reduce the computational costs from time series with their length textual prompts, we design an effective prompt to encourage the most essential temporal information to be encapsulated in the last token: only the last token is passed to downstream prediction.
Ranked #8 on
Time Series Forecasting
on ETTh1 (336) Multivariate
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search
Recently, with the help of fast SIMD-based implementations, Product Quantization (PQ) and its variants can often efficiently and accurately estimate the distances between the vectors and have achieved great success in the in-memory ANN search.
A Survey of Generative Techniques for Spatial-Temporal Data Mining
By integrating generative techniques and providing a standardized framework, the paper contributes to advancing the field and encourages researchers to explore the vast potential of generative techniques in spatial-temporal data mining.
Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics
In this study, we introduce a novel framework called Toast for learning general-purpose representations of road networks, along with its advanced counterpart DyToast, designed to enhance the integration of temporal dynamics to boost the performance of various time-sensitive downstream tasks.
A Study of Shape Modeling Against Noise
Shape modeling is a challenging task with many potential applications in computer vision and medical imaging.
AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
Air quality prediction and modelling plays a pivotal role in public health and environment management, for individuals and authorities to make informed decisions.
Spatial-Temporal Large Language Model for Traffic Prediction
In the ST-LLM, we define timesteps at each location as tokens and design a spatial-temporal embedding to learn the spatial location and global temporal patterns of these tokens.
KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy
To address this issue, we first present a novel Increment training strategy: instead of masking nodes (and reconstructing them), we add virtual nodes into the training graph so as to mitigate the graph gap issue naturally.
Defense Against Model Extraction Attacks on Recommender Systems
These gradients are used to compute a swap loss, which maximizes the loss of the student model.
Multi-Factor Spatio-Temporal Prediction based on Graph Decomposition Learning
The framework consists of two main components: an automatic graph decomposition module that decomposes the original graph structure inherent in ST data into subgraphs corresponding to different factors, and a decomposed learning network that learns the partial ST data on each subgraph separately and integrates them for the final prediction.
Self-Calibrated Cross Attention Network for Few-Shot Segmentation
Moreover, when calculating SCCA, we design a scaled-cosine mechanism to better utilize the support features for similarity calculation.
Ranked #12 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
OpenSiteRec: An Open Dataset for Site Recommendation
As a representative information retrieval task, site recommendation, which aims at predicting the optimal sites for a brand or an institution to open new branches in an automatic data-driven way, is beneficial and crucial for brand development in modern business.
Road Network Representation Learning: A Dual Graph based Approach
The constructed hypergraph would naturally capture the high-order relationships among roads with hyperedges.
Road Extraction with Satellite Images and Partial Road Maps
In this paper, we propose to conduct road extraction based on satellite images and partial road maps, which is new.
High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations
Approximate K nearest neighbor (AKNN) search is a fundamental and challenging problem.
Region Embedding with Intra and Inter-View Contrastive Learning
Motivated by the success of contrastive learning for representation learning, we propose to leverage it for multi-view region representation learning and design a model called ReMVC (Region Embedding with Multi-View Contrastive Learning) by following two guidelines: i) comparing a region with others within each view for effective representation extraction and ii) comparing a region with itself across different views for cross-view information sharing.
On Inferring User Socioeconomic Status with Mobility Records
The DeepSEI model incorporates two networks called deep network and recurrent network, which extract the features of the mobility records from three aspects, namely spatiality, temporality and activity, one at a coarse level and the other at a detailed level.
Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams
Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties.
Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning
Detecting anomalous trajectories has become an important task in many location-based applications.
A Survey on Neural Open Information Extraction: Current Status and Future Directions
Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora.
Ranked #1 on
Open Information Extraction
on CaRB
Knowledge Base Construction
Natural Language Understanding
+2
Points-of-Interest Relationship Inference with Spatial-enriched Graph Neural Networks
As a fundamental component in location-based services, inferring the relationship between points-of-interests (POIs) is very critical for service providers to offer good user experience to business owners and customers.
A Reinforcement Learning Based R-Tree for Spatial Data Indexing in Dynamic Environments
Learned indices have been proposed to replace classic index structures like B-Tree with machine learning (ML) models.
Towards advancing the earthquake forecasting by machine learning of satellite data
Amongst the available technologies for earthquake research, remote sensing has been commonly used due to its unique features such as fast imaging and wide image-acquisition range.
Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning
Similar trajectory search is a fundamental problem and has been well studied over the past two decades.
Interaction-aware Kalman Neural Networks for Trajectory Prediction
Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.)
Robotics I.2.9; I.2.0
Representation Learning for Spatial Graphs
Recently, the topic of graph representation learning has received plenty of attention.
