Search Results for author:
Found 14 papers, 5 papers with code
PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning
However, current approaches typically either train adapters on individual tasks or distill shared knowledge from source tasks, failing to fully exploit task-specific knowledge and the correlation between source and target tasks.
Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniques
This collaboration harnesses the sophisticated linguistic capabilities of LLMs to improve the contextual understanding and adaptability of graph models, thereby broadening the scope and potential of GRL.
JumpCoder: Go Beyond Autoregressive Coder via Online Modification
While existing code large language models (code LLMs) exhibit impressive capabilities in code generation, their autoregressive sequential generation inherently lacks reversibility.
ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt
Based on this framework, we propose a prompt-based transferability test to find the most relevant pretext task in order to reduce the semantic gap.
Calibration of Time-Series Forecasting Transformers: Detecting and Adapting Context-Driven Distribution Shift
In this paper, we introduce a universal calibration methodology for the detection and adaptation of CDS with a trained Transformer model.
Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank
Unbiased Learning to Rank (ULTR) aims to train unbiased ranking models from biased click logs, by explicitly modeling a generation process for user behavior and fitting click data based on examination hypothesis.
HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer
To bridge this gap, in this paper we investigate the representation learning on HINs with Graph Transformer, and propose a novel model named HINormer, which capitalizes on a larger-range aggregation mechanism for node representation learning.
Scalar is Not Enough: Vectorization-based Unbiased Learning to Rank
Most of the current ULTR methods are based on the examination hypothesis (EH), which assumes that the click probability can be factorized into two scalar functions, one related to ranking features and the other related to bias factors.
Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling
Sequential user behavior modeling plays a crucial role in online user-oriented services, such as product purchasing, news feed consumption, and online advertising.
MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
Nowadays, driven by the increasing concern on diet and health, food computing has attracted enormous attention from both industry and research community.
A Machine Learning Framework for Data Ingestion in Document Images
Paper documents are widely used as an irreplaceable channel of information in many fields, especially in financial industry, fostering a great amount of demand for systems which can convert document images into structured data representations.
Reference Network for Neural Machine Translation
Neural Machine Translation (NMT) has achieved notable success in recent years.
Compositional Coding for Collaborative Filtering
However, CF with binary codes naturally suffers from low accuracy due to limited representation capability in each bit, which impedes it from modeling complex structure of the data.
Online Bayesian Collaborative Topic Regression
In this paper, we propose a novel scheme of Online Bayesian Collaborative Topic Regression (OBCTR) which is efficient and scalable for learning from data streams.
