Search Results for author:
Found 8 papers, 1 papers with code
Exploring Loss Landscapes through the Lens of Spin Glass Theory
Specifically, we used (1) random walk in the parameter space of DNNs to unravel the structures in their loss landscape; (2) a permutation-interpolation protocol to study the connection between copies of identical regions in the loss landscape due to the permutation symmetry in the hidden layers; (3) hierarchical clustering to reveal the hierarchy among trained solutions of DNNs, reminiscent of the so-called Replica Symmetry Breaking (RSB) phenomenon (i. e. the Parisi solution) in spin glass; (4) finally, we examine the relationship between the ruggedness of DNN's loss landscape and its generalizability, showing an improvement of flattened minima.
Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors
The proliferation of fake news has had far-reaching implications on politics, the economy, and society at large.
Aligning Large Language Models for Controllable Recommendations
Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable, and controllable.
Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation
Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications.
Towards Fine-Grained Reasoning for Fake News Detection
The detection of fake news often requires sophisticated reasoning skills, such as logically combining information by considering word-level subtle clues.
Fake News Detection through Graph Comment Advanced Learning
Yet, the popularity of social media also provides opportunities to better detect fake news.
Fake News Detection
Representation Learning
Social and Information Networks
Addressing Time Bias in Bipartite Graph Ranking for Important Node Identification
The problem of ranking the nodes in bipartite networks is valuable for many real-world applications.
Predicting missing links via correlation between nodes
As a fundamental problem in many different fields, link prediction aims to estimate the likelihood of an existing link between two nodes based on the observed information.
