Search Results for author:
Found 45 papers, 18 papers with code
Towards Bridging Generalization and Expressivity of Graph Neural Networks
Expressivity and generalization are two critical aspects of graph neural networks (GNNs).
Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
As text-to-image diffusion models become advanced enough for commercial applications, there is also increasing concern about their potential for malicious and harmful use.
Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
We further analyze that GNNs with residual connections, a well-known solution to help gradient flow in deep architecture, introduce $\textit{gradient expansion}$, a phenomenon of the gradient explosion in diverse directions.
Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone.
Semi-nonparametric models of multidimensional matching: an optimal transport approach
This paper proposes empirically tractable multidimensional matching models, focusing on worker-job matching.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
Ranked #5 on
MMR total
on MRR-Benchmark
(using extra training data)
Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
Graph Neural Network (GNN) resembles the diffusion process, leading to the over-smoothing of learned representations when stacking many layers.
Generalization of Graph Neural Networks through the Lens of Homomorphism
In this work, we propose to study the generalization of GNNs through a novel perspective - analyzing the entropy of graph homomorphism.
Local Vertex Colouring Graph Neural Networks
Specifically, we propose a new vertex colouring scheme and demonstrate that classical search algorithms can efficiently compute graph representations that extend beyond the 1-WL.
Test Time Embedding Normalization for Popularity Bias Mitigation
Popularity bias is a widespread problem in the field of recommender systems, where popular items tend to dominate recommendation results.
EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
Data augmentation plays a critical role in improving model performance across various domains, but it becomes challenging with graph data due to their complex and irregular structure.
Graph Generation with $K^2$-trees
Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis.
Robust Evaluation of Diffusion-Based Adversarial Purification
We analyze the current practices and provide a new guideline for measuring the robustness of purification methods against adversarial attacks.
Feature Unlearning for Pre-trained GANs and VAEs
We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs.
SpReME: Sparse Regression for Multi-Environment Dynamic Systems
Learning dynamical systems is a promising avenue for scientific discoveries.
Substructure-Atom Cross Attention for Molecular Representation Learning
Designing a neural network architecture for molecular representation is crucial for AI-driven drug discovery and molecule design.
Hyperbolic VAE via Latent Gaussian Distributions
We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose latent space consists of a set of Gaussian distributions.
Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering
While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs.
Ranked #34 on
Node Classification
on Squirrel
Few-Shot Unlearning by Model Inversion
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model.
MetaSSD: Meta-Learned Self-Supervised Detection
There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unseen symbols.
Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns
Skeleton sequences are compact and lightweight.
A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning
We present a rotated hyperbolic wrapped normal distribution (RoWN), a simple yet effective alteration of a hyperbolic wrapped normal distribution (HWN).
ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark
To this end, we present a review in the form of a taxonomy on existing works of skeleton-based action recognition.
Anonymization for Skeleton Action Recognition
Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the privacy of subjects while having competitive recognition performance.
Robust Deep Learning from Crowds with Belief Propagation
Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers.
Vaccination strategies and transmission of COVID-19: evidence across advanced countries
Conditional on first-dose coverage, an increased fraction with two doses appears to offer no further reductions in new cases and deaths.
Neural Network Classifier as Mutual Information Evaluator
We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators.
Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
Such GNNs are incapable of learning relative positions between graph nodes within a graph.
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.
Ranked #27 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Invertible Denoising Network: A Light Solution for Real Noise Removal
InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise.
Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
The proposed model is shown to generalize well to both homophilic and heterophilic graphs.
A Body Part Embedding Model With Datasets for Measuring 2D Human Motion Similarity
Furthermore, in order to compute the motion similarity from these datasets, we propose a deep learning model that produces motion embeddings suitable for measuring the similarity between different motions of each human body part.
Global Node Attentions via Adaptive Spectral Filters
The proposed model has been shown to generalize well to both assortative and disassortative graphs.
word2word: A Collection of Bilingual Lexicons for 3,564 Language Pairs
We wrap our dataset and model in an easy-to-use Python library, which supports downloading and retrieving top-k word translations in any of the supported language pairs as well as computing top-k word translations for custom parallel corpora.
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption.
Softmax Is Not an Artificial Trick: An Information-Theoretic View of Softmax in Neural Networks
Under this view, we can naturally and mathematically derive log-softmax as an inherent component in a neural network for evaluating the conditional mutual information between network output vectors and labels given an input datum.
Neural Dynamic Programming for Musical Self Similarity
We present a neural sequence model designed specifically for symbolic music.
Self-Bounded Prediction Suffix Tree via Approximate String Matching
Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction.
Joint Modeling of Topics, Citations, and Topical Authority in Academic Corpora
Second, it models each author's influence on citations of a paper based on the topics of the cited papers, as well as the citing papers.
Computer Assisted Composition with Recurrent Neural Networks
For the case of highly permissive constraint sets, we find that sampling is to be preferred due to the overly regular nature of the optimisation based results.
Probabilistic Knowledge Graph Construction: Compositional and Incremental Approaches
Knowledge graph construction consists of two tasks: extracting information from external resources (knowledge population) and inferring missing information through a statistical analysis on the extracted information (knowledge completion).
Hierarchical learning of grids of microtopics
The counting grid is a grid of microtopics, sparse word/feature distributions.
Hierarchical Dirichlet Scaling Process
We present the \textit{hierarchical Dirichlet scaling process} (HDSP), a Bayesian nonparametric mixed membership model.
