Search Results for author:
Found 18 papers, 9 papers with code
Communication-Efficient Distributed PCA by Riemannian Optimization
In this paper, we study the leading eigenvector problem in a statistically distributed setting and propose a communication-efficient algorithm based on Riemannian optimization, which trades local computation for global communication.
S-LoRA: Scalable Low-Rank Adaptation for Class Incremental Learning
Continual Learning with foundation models has recently emerged as a promising approach to harnessing the power of pre-trained models for sequential tasks.
Learning Where to Edit Vision Transformers
Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintended effects on unrelated examples.
Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generation
However, most approaches employ a global alignment approach to learn the knowledge from different modalities that may fail to capture fine-grained information, such as molecule-and-text fragments and stereoisomeric nuances, which is crucial for downstream tasks.
Annotation-guided Protein Design with Multi-Level Domain Alignment
In this paper, we propose Protein-Annotation Alignment Generation, PAAG, a multi-modality protein design framework that integrates the textual annotations extracted from protein database for controllable generation in sequence space.
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.
Concept-wise Fine-tuning Matters in Preventing Negative Transfer
A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wide array of target datasets.
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers.
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers.
Can Pre-trained Models Really Learn Better Molecular Representations for AI-aided Drug Discovery?
Self-supervised pre-training is gaining increasingly more popularity in AI-aided drug discovery, leading to more and more pre-trained models with the promise that they can extract better feature representations for molecules.
Learning to generate imaginary tasks for improving generalization in meta-learning
The success of meta-learning on existing benchmarks is predicated on the assumption that the distribution of meta-training tasks covers meta-testing tasks.
Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport
In this paper, we present a novel optimal transport-based fine-tuning framework called GTOT-Tuning, namely, Graph Topology induced Optimal Transport fine-Tuning, for GNN style backbones.
Ranked #1 on
Graph Classification
on HIV
DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations
AI-aided drug discovery (AIDD) is gaining increasing popularity due to its promise of making the search for new pharmaceuticals quicker, cheaper and more efficient.
Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery
More recently, there has been a surge of interest in employing machine learning approaches to expedite the drug discovery process where virtual screening for hit discovery and ADMET prediction for lead optimization play essential roles.
Frustratingly Easy Transferability Estimation
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on a target task and prevent negative transfer.
Improving Generalization in Meta-learning via Task Augmentation
Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.
Accelerate Learning of Deep Hashing With Gradient Attention
Recent years have witnessed the success of learning to hash in fast large-scale image retrieval.
Online Hashing
Specifically, a new loss function is proposed to measure the similarity loss between a pair of data samples in hamming space.
