However, in practice, due to various challenges such as limited computational resources and data privacy concerns, users in need of models often cannot train machine learning models locally.
Signed graphs are valuable for modeling complex relationships with positive and negative connections, and Signed Graph Neural Networks (SGNNs) have become crucial tools for their analysis.
We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models.
To accomplish the above goals, we propose an intuitive and novel framework, MLPST, a pure multi-layer perceptron architecture for traffic prediction.
Then, we generate representative and common spatio-temporal patterns as global nodes to reflect a global dependency between sensors and provide auxiliary information for spatio-temporal dependency learning.
We devise a spatio-temporal transformer and a parameter-sharing training scheme to address the common knowledge among different spatio-temporal attributes.
One of the primary obstacles to current research in this field is the absence of a comprehensive curated benchmark suite to study the flow behaviors under network scenarios.
Previous works identify the problem of information mixing in the CLIP text encoder and introduce the T5 text encoder or incorporate strong prior knowledge to assist with the alignment.
To recommend cold items, existing federated recommendation models require collecting new interactions from users and retraining the model, which is time-consuming and poses a privacy threat to users' sensitive information.
To cope with the problems above, we propose an Automated Spatio-Temporal multi-task Learning (AutoSTL) method to handle multiple spatio-temporal tasks jointly.
Sequential recommender systems aim to predict users' next interested item given their historical interactions.
Non-intrusive load monitoring (NILM) aims to decompose aggregated electrical usage signal into appliance-specific power consumption and it amounts to a classical example of blind source separation tasks.
In this paper, we propose a novel and flexible conditional diffusion model by introducing conditions into the forward process.
Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings.
These imply that the gap corresponds to the lost information of the image, and we can reconstruct the image by filling the gap.
Explainable information retrieval is an emerging research area aiming to make transparent and trustworthy information retrieval systems.
These properties may have certain relationships with the word saliency, which is of great help for studying the explainability of the model predictions.
We introduce SparcAssist, a general-purpose risk assessment tool for the machine learning models trained for language tasks.
Score-based generative models involve sequentially corrupting the data distribution with noise and then learns to recover the data distribution based on score matching.
It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback.
Therefore, we propose a Position-based Contributive Embeddings (PosCE) to highlight the historical reference to special position aspect.
Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm.
However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned.
The technology of dynamic map fusion among networked vehicles has been developed to enlarge sensing ranges and improve sensing accuracies for individual vehicles.
Are humans consistently better at selecting features that make image recognition more accurate?
In this paper, we compute the sum of the Betti numbers for 6 of the 7 families of smooth Hilbert schemes over projective space.
Algebraic Geometry 14C05 (Primary), 14F25 (Secondary)
Then, in a wideband RIS-aided cell-free network, we formulate the problem of joint precoding design at BSs and RISs to maximize the network capacity.
This paper addresses the task of query-focused video summarization, which takes user's query and a long video as inputs and aims to generate a query-focused video summary.
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE.
In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings.
Inspired by Koch's Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector.