Search Results for author:
Found 20 papers, 6 papers with code
DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue \citep{lewis2020retrieval}.
Enhancing Token Filtering Efficiency in Large Language Model Training with Collider
Utility assessments of training TinyLlama on 15B tokens indicate that Collider sustains the utility advancements of token filtering by relatively improving model utility by 16. 3% comparing to regular training, and reduces training time from 4. 7 days to 3. 5 days using 8 GPUs.
mFabric: An Efficient and Scalable Fabric for Mixture-of-Experts Training
Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named \emph{experts}, on a per-token basis.
Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
Shopping MMLU consists of 57 tasks covering 4 major shopping skills: concept understanding, knowledge reasoning, user behavior alignment, and multi-linguality, and can thus comprehensively evaluate the abilities of LLMs as general shop assistants.
Exploiting Student Parallelism for Low-latency GPU Inference of BERT-like Models in Online Services
In this paper, we present Academus for low-latency online inference of BERT-like models.
PackVFL: Efficient HE Packing for Vertical Federated Learning
To this core, we propose PackVFL, an efficient VFL framework based on packed HE (PackedHE), to accelerate the existing HE-based VFL algorithms.
Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities
To address the problem, we propose TransGTR, a transferable structure learning framework for traffic forecasting that jointly learns and transfers the graph structures and forecasting models across cities.
A Survey on Vertical Federated Learning: From a Layered Perspective
From the hardware layer to the vertical federated system layer, researchers contribute to various aspects of VFL.
Federated Learning without Full Labels: A Survey
Therefore, the problem of federated learning without full labels is important in real-world FL applications.
Secure Forward Aggregation for Vertical Federated Neural Networks
In this paper, we focus on SplitNN, a well-known neural network framework in VFL, and identify a trade-off between data security and model performance in SplitNN.
Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
However, the inability of GNNs to model substructures in graphs remains a significant drawback.
Ternary Hashing
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts.
Rethinking Uncertainty in Deep Learning: Whether and How it Improves Robustness
Deep neural networks (DNNs) are known to be prone to adversarial attacks, for which many remedies are proposed.
EPNE: Evolutionary Pattern Preserving Network Embedding
In this paper, we propose EPNE, a temporal network embedding model preserving evolutionary patterns of the local structure of nodes.
Graph Structural-topic Neural Network
Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently.
Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective
Federated Learning (FL) proposed in recent years has received significant attention from researchers in that it can bring separate data sources together and build machine learning models in a collaborative but private manner.
GraLSP: Graph Neural Networks with Local Structural Patterns
Specifically, we capture local graph structures via random anonymous walks, powerful and flexible tools that represent structural patterns.
DANE: Domain Adaptive Network Embedding
Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data.
SecureBoost: A Lossless Federated Learning Framework
This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set.
ICFVR 2017: 3rd International Competition on Finger Vein Recognition
The development of finger vein recognition algorithms heavily depends on large-scale real-world data sets.
