Search Results for author:
Found 42 papers, 15 papers with code
Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference.
Robustness May be More Brittle than We Think under Different Degrees of Distribution Shifts
This indicates that while pre-trained representations may help improve downstream in-distribution performance, they could have minimal or even adverse effects on generalization in certain OOD scenarios of the downstream task if not used properly.
A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment
Training large language models (LLMs) with open-domain instruction data has yielded remarkable success in aligning to end tasks and human preferences.
A Causal Framework to Unify Common Domain Generalization Approaches
Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s).
Two-Stage Holistic and Contrastive Explanation of Image Classification
The need to explain the output of a deep neural network classifier is now widely recognized.
Causal Document-Grounded Dialogue Pre-training
To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora.
Contrastive Domain Generalization via Logit Attribution Matching
Domain Generalization (DG) is an important open problem in machine learning.
Semi-Supervised Lifelong Language Learning
In this paper, we explore a novel setting, semi-supervised lifelong language learning (SSLL), where a model learns sequentially arriving language tasks with both labeled and unlabeled data.
ViT-CX: Causal Explanation of Vision Transformers
Despite the popularity of Vision Transformers (ViTs) and eXplainable AI (XAI), only a few explanation methods have been designed specially for ViTs thus far.
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation
Furthermore, inspired by recent work in bridging label smoothing and knowledge distillation, our work utilizes self-knowledge as a prior label distribution in softening target labels, and presents theoretical support for the regularization effect by knowledge distillation and the dynamic smoothing parameter.
Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model
The question is answered in our work with the concept of model calibration; we view a teacher model not only as a source of knowledge but also as a gauge to detect miscalibration of a student.
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems.
Deep Clustering with Features from Self-Supervised Pretraining
A deep clustering model conceptually consists of a feature extractor that maps data points to a latent space, and a clustering head that groups data points into clusters in the latent space.
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available.
Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization
A common approach is to map a given sentence to content representation that is free of style, and the content representation is fed to a decoder with a target style.
DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling
In this paper, we develop DeepRapper, a Transformer-based rap generation system that can model both rhymes and rhythms.
Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network.
Handling Collocations in Hierarchical Latent Tree Analysis for Topic Modeling
Topic modeling has been one of the most active research areas in machine learning in recent years.
Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
In previous work, the external document is utilized by (1) creating a context-aware document memory that integrates information from the document and the conversational context, and then (2) generating responses referring to the memory.
Not All Attention Is Needed: Gated Attention Network for Sequence Data
Attention mechanisms compute input-dependent dynamic attention weights for aggregating a sequence of hidden states.
Learning to Abstract for Memory-augmented Conversational Response Generation
In this work, we propose a memory-augmented generative model, which learns to abstract from the training corpus and saves the useful information to the memory to assist the response generation.
Cleaned Similarity for Better Memory-Based Recommenders
In this paper, we analyze the spectral properties of the Pearson and the cosine similarity estimators, and we use tools from random matrix theory to argue that they suffer from noise and eigenvalues spreading.
Matrix Factorization Equals Efficient Co-occurrence Representation
We then use insights from random matrix theory (RMT) to show that picking the top eigenvectors corresponds to removing sampling noise from user/item co-occurrence matrices.
Using Taste Groups for Collaborative Filtering
In this paper, we propose as a novel method for addressing the lack of negative examples in implicit feedback.
Learning Hierarchical Item Categories from Implicit Feedback Data for Efficient Recommendations and Browsing
Categories created in this fashion are based on users' co-consumption of items.
Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion
An important characteristic of FNN structures learned this way is that they are sparse.
Building Sparse Deep Feedforward Networks using Tree Receptive Fields
We use Chow-Liu's algorithm to learn a tree-structured probabilistic model for the units at the current level, use the tree to identify subsets of units that are strongly correlated, and introduce a new unit with receptive field over the subsets.
Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clustering
We investigate a variant of variational autoencoders where there is a superstructure of discrete latent variables on top of the latent features.
Learning Parsimonious Deep Feed-forward Networks
Convolutional neural networks and recurrent neural networks are designed with network structures well suited to the nature of spacial and sequential data respectively.
A Novel Document Generation Process for Topic Detection based on Hierarchical Latent Tree Models
It is the new state-of-the-art for the hierarchical topic detection.
Conformative Filtering for Implicit Feedback Data
Implicit feedback is the simplest form of user feedback that can be used for item recommendation.
Latent Tree Analysis
Latent tree analysis seeks to model the correlations among a set of random variables using a tree of latent variables.
Topic Browsing for Research Papers with Hierarchical Latent Tree Analysis
The resulting topic model contains a hierarchy of topics so that users can browse the topics from the top level to the bottom level.
Sparse Boltzmann Machines with Structure Learning as Applied to Text Analysis
We are interested in exploring the possibility and benefits of structure learning for deep models.
Latent Tree Models for Hierarchical Topic Detection
The variables at other levels are binary latent variables, with those at the lowest latent level representing word co-occurrence patterns and those at higher levels representing co-occurrence of patterns at the level below.
Identification and classification of TCM syndrome types among patients with vascular mild cognitive impairment using latent tree analysis
Conclusions: A solution for the TCM syndrome classification problem associated with VMCI is established based on the latent tree analysis of unlabeled symptom survey data.
Progressive EM for Latent Tree Models and Hierarchical Topic Detection
It is as efficient as the state-of-the-art LDA-based method for hierarchical topic detection and finds substantially better topics and topic hierarchies.
Bayesian Adaptive Matrix Factorization With Automatic Model Selection
Low-rank matrix factorization has long been recognized as a fundamental problem in many computer vision applications.
A data-driven method for syndrome type identification and classification in traditional Chinese medicine
Conclusions: A data-driven method for TCM syndrome identification and classification is presented.
A Survey on Latent Tree Models and Applications
In data analysis, latent variables play a central role because they help provide powerful insights into a wide variety of phenomena, ranging from biological to human sciences.
Latent Tree Models and Approximate Inference in Bayesian Networks
We propose a novel method for approximate inference in Bayesian networks (BNs).
