paper-with-me

Papers

Controlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting

2020-10-13 · Ghazi Felhi, Joseph Leroux, Djamé Seddah

Even though Variational Autoencoders (VAEs) are widely used for semi-supervised learning, the reason why they work remains unclear. In fact, the addition of the unsupervised objective is most often vaguely described as a regularization. The strength of this regularization is controlled by down-weighting the objective on the unlabeled part of the training set. Through an analysis of the objective of semi-supervised VAEs, we observe that they use the posterior of the learned generative model to guide the inference model in learning the partially observed latent variable. We show that given this observation, it is possible to gain finer control on the effect of the unsupervised objective on the training procedure. Using importance weighting, we derive two novel objectives that prioritize either one of the partially observed latent variable, or the unobserved latent variable. Experiments on the IMDB english sentiment analysis dataset and on the AG News topic classification dataset show the improvements brought by our prioritization mechanism and exhibit a behavior that is inline with our description of the inner working of Semi-Supervised VAEs.

📄 PDF Abstract BibTeX arXiv:2010.06549

Code (2)

ghazi-f/SSPIWO 공식 구현 pytorch
ghazi-f/challenging-ssvaes pytorch

Tasks

Sentiment AnalysisTopic Classification

Similar Papers 제목 키워드 기반

Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

2026-03-07 · Kai Cheng, Hao Wang, Wei Guo, Weiwen Liu 외 arxiv

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deploymen…

Knowledge Distillation

Towards a Better Microcredit Decision

2022-08-23 · Mengnan Song, Jiasong Wang, Suisui Su

Reject inference comprises techniques to infer the possible repayment behavior of rejected cases. In this paper, we model credit in a brand new view by capturing the sequential pattern of interactions among multiple stag…

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

2026-02-02 · Jingwei Song, Meng Chen, Jie Xiao, Qingnan Ren 외 arxiv

Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward evaluation, and centralized learning. Distributing rollout …

Reinforcement Learning

SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling

2025-08-12 · Shixuan Sun, Siyuan Liang, Ruoyu Chen, Jianjie Huang 외 arxiv

Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing exter…

Image Retrieval

Contrastive Monotonic Pixel-Level Modulation

2022-07-23 · Kun Lu, Rongpeng Li, Honggang Zhang

Continuous one-to-many mapping is a less investigated yet important task in both low-level visions and neural image translation. In this paper, we present a new formulation called MonoPix, an unsupervised and contrastive…

Translation