Related papers: Learning Aggregation Functions
This paper focuses on the discrimination capacity of aggregation functions: these are the permutation invariant functions used by graph neural networks to combine the features of nodes. Realizing that the most powerful aggregation functions…
A generally intelligent learner should generalize to more complex tasks than it has previously encountered, but the two common paradigms in machine learning -- either training a separate learner per task or training a single learner for all…
Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL), which enables distributed model training without exposing raw data, with Retrieval-Augmented Generation (RAG), which improves the factual accuracy of…
Mobile keyboard suggestion is typically regarded as a word-level language modeling problem. Centralized machine learning technique requires massive user data collected to train on, which may impose privacy concerns for sensitive personal…
Federated learning has received great attention for its capability to train a large-scale model in a decentralized manner without needing to access user data directly. It helps protect the users' private data from centralized collecting.…
Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model architectures and have varying computational resources. Such…
Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification,…
In traffic prediction, the goal is to estimate traffic speed or flow in specific regions or road segments using historical data collected by devices deployed in each area. Each region or road segment can be viewed as an individual client…
Latent action learning infers pseudo-action labels from visual transitions, providing an approach to leverage internet-scale video for embodied AI. However, most methods learn latent actions without structural priors that encode the…
The unstructured nature of point clouds demands that local aggregation be adaptive to different local structures. Previous methods meet this by explicitly embedding spatial relations into each aggregation process. Although this coupled…
Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. Prior work has either hard-coded object-centric features,…
Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is…
Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they face limitations in internalizing the data they process and…
Conventional supervised learning assumes a stable input-output relationship. However, this assumption fails in open-ended training settings where the input-output relationship depends on hidden contexts. In this work, we formulate a more…
Human activity recognition (HAR) based on mobile sensors plays an important role in ubiquitous computing. However, the rise of data regulatory constraints precludes collecting private and labeled signal data from personal devices at scale.…
Machine learning is at the heart of managing the real-world problems associated with massive data. With the success of neural networks on such large-scale problems, more research in machine learning is being conducted now than ever before.…
The heterogeneous network is a robust data abstraction that can model entities of different types interacting in various ways. Such heterogeneity brings rich semantic information but presents nontrivial challenges in aggregating the…
Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation strategy to defend…
A key challenge in video enhancement and action recognition is to fuse useful information from neighboring frames. Recent works suggest establishing accurate correspondences between neighboring frames before fusing temporal information.…
We present a supervised-learning algorithm from graph data (a set of graphs) for arbitrary twice-differentiable loss functions and sparse linear models over all possible subgraph features. To date, it has been shown that under all possible…