Search Results for author:
Found 43 papers, 11 papers with code
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
Large Language Models (LLMs) can enhance their capabilities as AI assistants by integrating external tools, allowing them to access a wider range of information.
Rethinking Node Representation Interpretation through Relation Coherence
Understanding node representations in graph-based models is crucial for uncovering biases , diagnosing errors, and building trust in model decisions.
Improving Node Representation by Boosting Target-Aware Contrastive Loss
To bridge this gap, we introduce Target-Aware Contrastive Learning (Target-aware CL) which aims to enhance target task performance by maximizing the mutual information between the target task and node representations with a self-supervised learning process.
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge.
LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
To solve this problem, we embed a Large Language Model (LLM) as knowledge into the GNN explanation network to avoid the learning bias problem.
On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
We explore the use of Large Language Model (LLM-based) chatbots to power recommender systems.
MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals.
Node Similarities under Random Projections: Limits and Pathological Cases
Random Projections have been widely used to generate embeddings for various graph learning tasks due to their computational efficiency.
Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization
In many modern LLM applications, such as retrieval augmented generation, prompts have become programs themselves.
Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems.
The Use of Generative Search Engines for Knowledge Work and Complex Tasks
Until recently, search engines were the predominant method for people to access online information.
TnT-LLM: Text Mining at Scale with Large Language Models
Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application.
Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents
We show that users spend a lot of ``effort'' on these questions in terms of signals like clicks and session length, and that they are also challenging for GPT-4.
CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness
Our experiments explore the performance of CliqueParcel, including efficiency, faithfulness, and the trade-off between them.
Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers
Powerful large language models have facilitated the development of writing assistants that promise to significantly improve the quality and efficiency of composition and communication.
Automatic Pair Construction for Contrastive Post-training
Remarkably, our automatic contrastive post-training further improves the performance of Orca, already a state-of-the-art instruction learning model tuned with GPT-4 outputs, to outperform ChatGPT.
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
The traditional Dialogue State Tracking (DST) problem aims to track user preferences and intents in user-agent conversations.
Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies
However, using LLMs to generate a user intent taxonomy and apply it for log analysis can be problematic for two main reasons: (1) such a taxonomy is not externally validated; and (2) there may be an undesirable feedback loop.
Stationary Algorithmic Balancing For Dynamic Email Re-Ranking Problem
Email platforms need to generate personalized rankings of emails that satisfy user preferences, which may vary over time.
DYMOND: DYnamic MOtif-NoDes Network Generative Model
To address these issues, in this work we propose DYnamic MOtif-NoDes (DYMOND) -- a generative model that considers (i) the dynamic changes in overall graph structure using temporal motif activity and (ii) the roles nodes play in motifs (e. g., one node plays the hub role in a wedge, while the remaining two act as spokes).
Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
Experiments show that the ranking of nodes by scores using GRAPH-wGD is highly correlated with true bridgeness scores.
Creating generalizable downstream graph models with random projections
We investigate graph representation learning approaches that enable models to generalize across graphs: given a model trained using the representations from one graph, our goal is to apply inference using those same model parameters when given representations computed over a new graph, unseen during model training, with minimal degradation in inference accuracy.
Federated Graph Representation Learning using Self-Supervision
1. 7% gains compared to individual client specific self-supervised training and (2) we construct and introduce a new cross-silo dataset called Amazon Co-purchase Networks that have both the characteristics of the motivated problem setting.
Hindsight Learning for MDPs with Exogenous Inputs
Many resource management problems require sequential decision-making under uncertainty, where the only uncertainty affecting the decision outcomes are exogenous variables outside the control of the decision-maker.
Lightweight Compositional Embeddings for Incremental Streaming Recommendation
Most work in graph-based recommender systems considers a {\em static} setting where all information about test nodes (i. e., users and items) is available upfront at training time.
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
We find that the prediction performance of a wide range of GNN models is highly correlated with the node level assortativity.
Graph Learning
Node Classification on Non-Homophilic (Heterophilic) Graphs
Adversarial Graph Augmentation to Improve Graph Contrastive Learning
Self-supervised learning of graph neural networks (GNN) is in great need because of the widespread label scarcity issue in real-world graph/network data.
ReadNet: A Hierarchical Transformer Framework for Web Article Readability Analysis
Analyzing the readability of articles has been an important sociolinguistic task.
A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs
Our method uses a cross feedback paradigm wherein, an embedding model is used to guide the search of a rule mining system to mine rules and infer new facts.
A Collective Learning Framework to Boost GNN Expressiveness
Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node labels.
Cluster-Based Social Reinforcement Learning
Social Reinforcement Learning methods, which model agents in large networks, are useful for fake news mitigation, personalized teaching/healthcare, and viral marketing, but it is challenging to incorporate inter-agent dependencies into the models effectively due to network size and sparse interaction data.
Deep Lifetime Clustering
The goal of lifetime clustering is to develop an inductive model that maps subjects into $K$ clusters according to their underlying (unobserved) lifetime distribution.
Community detection over a heterogeneous population of non-aligned networks
Clustering and community detection with multiple graphs have typically focused on aligned graphs, where there is a mapping between nodes across the graphs (e. g., multi-view, multi-layer, temporal graphs).
Multi-level hypothesis testing for populations of heterogeneous networks
Current approaches to hypothesis testing for weighted networks typically requires thresholding the edge-weights, to transform the data to binary networks.
Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy
Recent work has combined Stein’s method with reproducing kernel Hilbert space theory to develop nonparametric goodness-of-fit tests for un-normalized probability distributions.
A Deep Learning Approach for Survival Clustering without End-of-life Signals
The goal of survival clustering is to map subjects (e. g., users in a social network, patients in a medical study) to $K$ clusters ranging from low-risk to high-risk.
Stochastic Gradient Descent for Relational Logistic Regression via Partial Network Crawls
Research in statistical relational learning has produced a number of methods for learning relational models from large-scale network data.
Size-Consistent Statistics for Anomaly Detection in Dynamic Networks
An important task in network analysis is the detection of anomalous events in a network time series.
Combining Gradient Boosting Machines with Collective Inference to Predict Continuous Values
Specifically, we propose a boosting algorithm for learning a collective inference model that predicts a continuous target variable.
Using Bayesian Network Representations for Effective Sampling from Generative Network Models
Bayesian networks (BNs) are used for inference and sampling by exploiting conditional independence among random variables.
Graphlet Decomposition: Framework, Algorithms, and Applications
From social science to biology, numerous applications often rely on graphlets for intuitive and meaningful characterization of networks at both the global macro-level as well as the local micro-level.
Learning the Latent State Space of Time-Varying Graphs
We use the two representations as inputs to a mixture model to learn the latent state transitions that correspond to important changes in the Email graph structure over time.
