Search Results for author:
Found 36 papers, 17 papers with code
PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance
We evaluate the latest LLMs, including the recent reasoner models QwQ-32B and Deepseek R1.
Knowledge-aware contrastive heterogeneous molecular graph learning
Molecular representation learning is pivotal in predicting molecular properties and advancing drug design.
Small Molecule Drug Discovery Through Deep Learning:Progress, Challenges, and Opportunities
Due to their excellent drug-like and pharmacokinetic properties, small molecule drugs are widely used to treat various diseases, making them a critical component of drug discovery.
Can Molecular Evolution Mechanism Enhance Molecular Representation?
We extract and analyze the changes in the evolutionary pathway and explore combining it with existing molecular representations.
DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts
Empirically, fewer layers are sufficient for message passing in smaller graphs, while larger graphs typically require deeper networks to capture long-range dependencies and global features.
Text-Guided Multi-Property Molecular Optimization with a Diffusion Language Model
TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby preventing error propagation during diffusion process.
Fragment-Masked Molecular Optimization
Molecular optimization is a crucial aspect of drug discovery, aimed at refining molecular structures to enhance drug efficacy and minimize side effects, ultimately accelerating the overall drug development process.
Node Level Graph Autoencoder: Unified Pretraining for Textual Graph Learning
Textual graph representation learning aims to generate low-dimensional feature embeddings from textual graphs that can improve the performance of downstream tasks.
Regressor-free Molecule Generation to Support Drug Response Prediction
As a result, we introduce regressor-free guidance molecule generation to ensure sampling within a more effective space and support DRP.
A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction
In the drug development engineering field, predicting novel drug-target interactions is extremely crucial. However, although existing methods have achieved high accuracy levels in predicting known drugs and drug targets, they fail to utilize global protein information during DTI prediction.
Hi-GMAE: Hierarchical Graph Masked Autoencoders
To ensure masking uniformity of subgraphs across these scales, we propose a novel coarse-to-fine strategy that initiates masking at the coarsest scale and progressively back-projects the mask to the finer scales.
Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
To this end, we introduce a novel structure-guided masking strategy (i. e., StructMAE), designed to refine the existing GMAE models.
Gradformer: Graph Transformer with Exponential Decay
Therefore, this paper presents Gradformer, a method innovatively integrating GT with the intrinsic inductive bias by applying an exponential decay mask to the attention matrix.
Modular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System
We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects, a task that requires fast, reactive, and accurately-timed robot motions.
CLDR: Contrastive Learning Drug Response Models from Natural Language Supervision
At the same time, in order to enhance the continuous representation capability of the numerical text, a common-sense numerical knowledge graph is introduced.
Ranked #1 on
Drug Response Prediction
on GDSC
Exploring Sparsity in Graph Transformers
Graph Transformers (GTs) have achieved impressive results on various graph-related tasks.
Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodes
Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning.
Zero-shot Learning of Drug Response Prediction for Preclinical Drug Screening
In this paper, we propose a zero-shot learning solution for the DRP task in preclinical drug screening.
Ranked #1 on
Zero-Shot Learning
on GDSCv2
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different alignment-forgetting trade-offs, we propose Heterogeneous Model Averaging (HMA) to Heterogeneously find various combination ratios of model layers.
Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
Deep neural networks (DNNs) have shown unprecedented success in object detection tasks.
On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
A pooling operation is essential for effective graph-level representation learning, where the node drop pooling has become one mainstream graph pooling technology.
Prompt-Learning for Cross-Lingual Relation Extraction
Experiments on WMT17-EnZh XRE also show the effectiveness of our Prompt-XRE against other competitive baselines.
State of the Art and Potentialities of Graph-level Learning
Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures.
Towards a Better Model with Dual Transformer for Drug Response Prediction
For the branch of cell lines genomics, we use the multi-headed attention mechanism to globally represent the genomics sequence.
Ranked #1 on
Drug Response Prediction
on GDSCv2
Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks
However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where significant redundancy exists.
CLNode: Curriculum Learning for Node Classification
Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.
Graph-level Neural Networks: Current Progress and Future Directions
To frame this survey, we propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling.
Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities
Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation.
EPPAC: Entity Pre-typing Relation Classification with Prompt AnswerCentralizing
To address these issues, a novel paradigm, Entity Pre-typing Relation Classification with Prompt Answer Centralizing(EPPAC) is proposed in this paper.
Two-dimensional flow field measurement of sediment-laden flow based on ultrasound image velocimetry
This paper proposes a novel particle image velocimetry (PIV) technique to generate an instantaneous two-dimensional velocity field for sediment-laden fluid based on the optical flow algorithm of ultrasound imaging.
BanditMTL: Bandit-based Multi-task Learning for Text Classification
Task variance regularization, which can be used to improve the generalization of Multi-task Learning (MTL) models, remains unexplored in multi-task text classification.
A Comprehensive Survey on Community Detection with Deep Learning
A community reveals the features and connections of its members that are different from those in other communities in a network.
Opinion Maximization in Social Trust Networks
However, the practical significance of the existing studies on this subject is limited for two reasons.
Social and Information Networks Computer Science and Game Theory J.4
Deep Learning for Community Detection: Progress, Challenges and Opportunities
As communities represent similar opinions, similar functions, similar purposes, etc., community detection is an important and extremely useful tool in both scientific inquiry and data analytics.
Learning Pregrasp Manipulation of Objects from Ungraspable Poses
In robotic grasping, objects are often occluded in ungraspable configurations such that no pregrasp pose can be found, eg large flat boxes on the table that can only be grasped from the side.
Robotics
Reaching, Grasping and Re-grasping: Learning Fine Coordinated Motor Skills
The performance of learned policy is evaluated on three different tasks: grasping a static target, grasping a dynamic target, and re-grasping.
Robotics
