More Like this

1. Learning from Mistakes – a Framework for Neural Architecture Search

   https://doi.org/10.1609/aaai.v36i9.21258  

   Garg, Bhanu; Zhang, Li; Sridhara, Pradyumna; Hosseini, Ramtin; Xing, Eric; Xie, Pengtao (June 2022, Proceedings of the AAAI Conference on Artificial Intelligence)

   Learning from one's mistakes is an effective human learning technique where the learners focus more on the topics where mistakes were made, so as to deepen their understanding. In this paper, we investigate if this human learning strategy can be applied in machine learning. We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision. We formulate LFM as a three-stage optimization problem: 1) learner learns; 2) learner re-learns focusing on the mistakes, and; 3) learner validates its learning. We develop an efficient algorithm to solve the LFM problem. We apply the LFM framework to neural architecture search on CIFAR-10, CIFAR-100, and Imagenet. Experimental results strongly demonstrate the effectiveness of our model. 

   more » « less
2. In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness

   Collins, L; Parulekar, A; Mokhtari, A; Sanghavi, S; Shakkottai, S (May 2024, https://doi.org/10.48550/arXiv.2402.11639)

   A striking property of transformers is their ability to perform in-context learning (ICL), a machine learning framework in which the learner is presented with a novel context during inference implicitly through some data, and tasked with making a prediction in that context. As such, that learner must adapt to the context without additional training. We explore the role of softmax attention in an ICL setting where each context encodes a regression task. We show that an attention unit learns a window that it uses to implement a nearest-neighbors predictor adapted to the landscape of the pretraining tasks. Specifically, we show that this window widens with decreasing Lipschitzness and increasing label noise in the pretraining tasks. We also show that on low-rank, linear problems, the attention unit learns to project onto the appropriate subspace before inference. Further, we show that this adaptivity relies crucially on the softmax activation and thus cannot be replicated by the linear activation often studied in prior theoretical analyses. 

   more » « less
3. Federated Graph Learning with Graphless Clients

   Fu, Xingbo; Wang, Song; Dong, Yushun; Zhang, Binchi; Chen, Chen; Li, Jundong (October 2024, Transactions on machine learning research)

   Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while other clients (i.e. graphless clients) may only have node features. This naturally leads to a novel problem in FGL: how to jointly train a model over distributed graph data with graphless clients? In this paper, we propose a novel framework FedGLS to tackle the problem in FGL with graphless clients. In FedGLS, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. 

   more » « less
4. RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning

   https://doi.org/10.1609/aaai.v34i01.5413  

   Jiang, Nan; Jin, Sheng; Duan, Zhiyao; Zhang, Changshui (June 2020, Proceedings of the AAAI Conference on Artificial Intelligence)

   This paper presents a deep reinforcement learning algorithm for online accompaniment generation, with potential for real-time interactive human-machine duet improvisation. Different from offline music generation and harmonization, online music accompaniment requires the algorithm to respond to human input and generate the machine counterpart in a sequential order. We cast this as a reinforcement learning problem, where the generation agent learns a policy to generate a musical note (action) based on previously generated context (state). The key of this algorithm is the well-functioning reward model. Instead of defining it using music composition rules, we learn this model from monophonic and polyphonic training data. This model considers the compatibility of the machine-generated note with both the machine-generated context and the human-generated context. Experiments show that this algorithm is able to respond to the human part and generate a melodic, harmonic and diverse machine part. Subjective evaluations on preferences show that the proposed algorithm generates music pieces of higher quality than the baseline method. 

   more » « less
5. Distributed Multi-Task Learning with Shared Representation

   Wang, Jialei; Kolar, Mladen; Srebro, Nathan (March 2016, arXiv.org)

   We study the problem of distributed multitask learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with samples for the task available locally on the machine, and study communication-efficient methods for exploiting the shared structure. 

   more » « less