Search Results for author:
Found 26 papers, 15 papers with code
Retrieval-Augmented Generation with Hierarchical Knowledge
Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks.
Can Large Language Models Help Experimental Design for Causal Discovery?
Designing proper experiments and selecting optimal intervention targets is a longstanding problem in scientific or causal discovery.
DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization
A popular approach to addressing this issue is invariant learning (IL), in which the model is compiled to focus on invariant features instead of spurious features by adding strong constraints during training.
BrainOOD: Out-of-distribution Generalizable Brain Network Analysis
Graph Neural Networks (GNNs) have shown promising in analyzing brain networks, but there are two major challenges in using GNNs: (1) distribution shifts in multi-site brain network data, leading to poor Out-of-Distribution (OOD) generalization, and (2) limited interpretability in identifying key brain regions critical to neurological disorders.
Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
In SCIE, the instructions are treated as the treatment, and textual features are used to process natural language, establishing causal relationships through treatments between instructions and downstream tasks.
Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration
Generalization has long been a central challenge in real-world image restoration.
On the Comparison between Multi-modal and Single-modal Contrastive Learning
Our analysis provides a unified framework that can characterize the optimization and generalization of both single-modal and multi-modal contrastive learning.
UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation
Equipped with this tokenizer, UniMoT can unify molecule and text modalities under a shared token representation and an autoregressive training paradigm, enabling it to interpret molecules as a foreign language and generate them as text.
Empowering Graph Invariance Learning with Deep Spurious Infomax
To bridge this gap, we introduce a novel graph invariance learning paradigm, which induces a robust and general inductive bias.
HIGHT: Hierarchical Graph Tokenization for Graph-Language Alignment
As LLMs are predominantly trained with 1D text data, most existing approaches adopt a graph neural network to represent a graph as a series of node tokens and feed these tokens to LLMs for graph-language alignment.
How Interpretable Are Interpretable Graph Neural Networks?
Extracting the desired interpretable subgraph requires an accurate approximation of SubMT, yet we find that the existing XGNNs can have a huge gap in fitting SubMT.
A Sober Look at the Robustness of CLIPs to Spurious Features
Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet.
Discovery of the Hidden World with Large Language Models
Meanwhile, COAT also adopts CDs to find causal relations among the identified variables as well as to provide feedback to LLMs to iteratively refine the proposed factors.
Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications.
Enhancing Evolving Domain Generalization through Dynamic Latent Representations
However, in non-stationary tasks where new domains evolve in an underlying continuous structure, such as time, merely extracting the invariant features is insufficient for generalization to the evolving new domains.
Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes
Surprisingly, DeepSet outperforms transformers across a variety of distribution shifts, implying that preserving permutation invariance symmetry to input demonstrations is crucial for OOD ICL.
Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs.
Towards out-of-distribution generalizable predictions of chemical kinetics properties
Under this framework, we create comprehensive datasets to benchmark (1) the state-of-the-art ML approaches for reaction prediction in the OOD setting and (2) the state-of-the-art graph OOD methods in kinetics property prediction problems.
Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features.
Dataset and Baseline System for Multi-lingual Extraction and Normalization of Temporal and Numerical Expressions
Temporal and numerical expression understanding is of great importance in many downstream Natural Language Processing (NLP) and Information Retrieval (IR) tasks.
RLTP: Reinforcement Learning to Pace for Delayed Impression Modeling in Preloaded Ads
In a whole delivery period, advertisers usually desire a certain impression count for the ads, and they also expect that the delivery performance is as good as possible (e. g., obtaining high click-through rate).
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data.
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability
Recently Graph Injection Attack (GIA) emerges as a practical attack scenario on Graph Neural Networks (GNNs), where the adversary can merely inject few malicious nodes instead of modifying existing nodes or edges, i. e., Graph Modification Attack (GMA).
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e. g., images), studies on graph data are still limited.
Calibrating and Improving Graph Contrastive Learning
To assess the discrepancy between the prediction and the ground-truth in the downstream tasks for these contrastive pairs, we adapt the expected calibration error (ECE) to graph contrastive learning.
Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
In this paper, we propose self-enhanced GNN (SEG), which improves the quality of the input data using the outputs of existing GNN models for better performance on semi-supervised node classification.
