Search Results for author: Gangwei Jiang

Found 9 papers, 3 papers with code

Understanding and Patching Compositional Reasoning in LLMs

no code implementations22 Feb 2024 Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying WEI

LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.

Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt

1 code implementation19 Oct 2023 Gangwei Jiang, Caigao Jiang, Siqiao Xue, James Y. Zhang, Jun Zhou, Defu Lian, Ying WEI

In this work, we first investigate such anytime fine-tuning effectiveness of existing continual pre-training approaches, concluding with unanimously decreased performance on unseen domains.

Transfer Learning

Deep Task-specific Bottom Representation Network for Multi-Task Recommendation

no code implementations11 Aug 2023 Qi Liu, Zhilong Zhou, Gangwei Jiang, Tiezheng Ge, Defu Lian

In this paper, we focus on the bottom representation learning of MTL in RS and propose the Deep Task-specific Bottom Representation Network (DTRN) to alleviate the negative transfer problem.

Multi-Task Learning Recommendation Systems +1

Continual Learning in Predictive Autoscaling

no code implementations29 Jul 2023 Hongyan Hao, Zhixuan Chu, Shiyi Zhu, Gangwei Jiang, Yan Wang, Caigao Jiang, James Zhang, Wei Jiang, Siqiao Xue, Jun Zhou

In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set.

Continual Learning Density Estimation

Self-Supervised Text Erasing with Controllable Image Synthesis

no code implementations27 Apr 2022 Gangwei Jiang, Shiyao Wang, Tiezheng Ge, Yuning Jiang, Ying WEI, Defu Lian

The synthetic training images with erasure ground-truth are then fed to train a coarse-to-fine erasing network.

Image Generation

Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure

1 code implementation2 Mar 2021 Jin Chen, Tiezheng Ge, Gangwei Jiang, Zhiqiang Zhang, Defu Lian, Kai Zheng

Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.

Efficient Exploration Thompson Sampling

Automated Creative Optimization for E-Commerce Advertising

1 code implementation28 Feb 2021 Jin Chen, Ju Xu, Gangwei Jiang, Tiezheng Ge, Zhiqiang Zhang, Defu Lian, Kai Zheng

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.

AutoML Click-Through Rate Prediction +2

Cannot find the paper you are looking for? You can Submit a new open access paper.