Search Results for author:
Found 30 papers, 10 papers with code
Searching to Exploit Memorization Effect in Learning with Noisy Labels
Sample selection approaches are popular in robust learning from noisy labels.
Alignment of Diffusion Models: Fundamentals, Challenges, and Future
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications.
CodeGraph: Enhancing Graph Reasoning of LLMs with Code
Compared to the existing methods, CodeGraph demonstrates strong performance on arithmetic problems in graph tasks and offers a more controllable and interpretable approach to the reasoning process.
You Only Merge Once: Learning the Pareto Set of Preference-Aware Model Merging
In only one merging process, the proposed parameter-efficient structure can generate the whole Pareto set of merged models, each representing the Pareto-optimal model for a given user-specified preference.
Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks
The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models.
Nonparametric Teaching for Multiple Learners
In MINT, the teacher aims to instruct multiple learners, with each learner focusing on learning a scalar-valued target model.
Positive-Unlabeled Node Classification with Structure-aware Graph Learning
We also propose a regularizer to align the model with graph structure.
Implicit Concept Removal of Diffusion Models
Subsequently, the model is optimized to identify and disentangle this information, which is then adopted as negative prompts during generation.
PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
We hope PIXART-$\alpha$ will provide new insights to the AIGC community and startups to accelerate building their own high-quality yet low-cost generative models from scratch.
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training
Compared with the existing methods, GrowCLIP improves 2. 3% average top-1 accuracy on zero-shot image classification of 9 downstream tasks.
Non-autoregressive Conditional Diffusion Models for Time Series Prediction
In this paper, we propose TimeDiff, a non-autoregressive diffusion model that achieves high-quality time series prediction with the introduction of two novel conditioning mechanisms: future mixup and autoregressive initialization.
Nonparametric Iterative Machine Teaching
In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model.
An Adaptive Policy to Employ Sharpness-Aware Minimization
Sharpness-aware minimization (SAM), which searches for flat minima by min-max optimization, has been shown to be useful in improving model generalization.
Leveraging per Image-Token Consistency for Vision-Language Pre-training
(2) Under-utilization of the unmasked tokens: CMLM primarily focuses on the masked token but it cannot simultaneously leverage other tokens to learn vision-language associations.
Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization
While the optimization problem is nonconvex and nonsmooth, we show that its critical points still have good statistical performance on the tensor completion problem.
Effective Meta-Regularization by Kernelized Proximal Regularization
We study the problem of meta-learning, which has proved to be advantageous to accelerate learning new tasks with a few samples.
Multi-Subspace Structured Meta-Learning
We propose a MUlti-Subspace structured Meta-Learning (MUSML) algorithm to learn the subspace bases.
Improving Meta-Continual Learning Representations with Representation Replay
In this paper, we remove this inconsistency in the use of ER and improve continual learning representations by integrating ER also into meta-training.
Fast Deterministic Stackelberg Actor-Critic
Most advanced Actor-Critic (AC) approaches update the actor and critic concurrently through (stochastic) Gradient Descents (GD), which may be trapped into bad local optimality due to the instability of these simultaneous updating schemes.
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network
This allows the temporal dynamics to be well captured by a set of multi-resolution temporal clusters.
Normalization Helps Training of Quantized LSTM
The long-short-term memory (LSTM), though powerful, is memory and computa\x02tion expensive.
Searching to Exploit Memorization Effect in Learning from Corrupted Labels
Sample selection approaches are popular in robust learning from noisy labels.
Policy Tree Network
However, decision-time planning with implicit dynamics models in continuous action space has proven to be a difficult problem.
Model-based Reinforcement Learning
Policy Gradient Methods
+4
Policy Prediction Network: Model-Free Behavior Policy with Model-Based Learning in Continuous Action Space
This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces.
Efficient Neural Interaction Function Search for Collaborative Filtering
Motivated by the recent success of automated machine learning (AutoML), we propose in this paper the search for simple neural interaction functions (SIF) in CF.
Efficient Low-Rank Semidefinite Programming with Robust Loss Functions
In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions.
Generalizing from a Few Examples: A Survey on Few-Shot Learning
Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small.
Side Information Fusion for Recommender Systems over Heterogeneous Information Network
Collaborative filtering (CF) has been one of the most important and popular recommendation methods, which aims at predicting users' preferences (ratings) based on their past behaviors.
Fast Second Order Stochastic Backpropagation for Variational Inference
We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well.
Fast Second-Order Stochastic Backpropagation for Variational Inference
We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well.
