Learning dynamical systems is a promising avenue for scientific discoveries. However, capturing the governing dynamics in multiple environments still remains a challenge: model-based approaches rely on the fidelity of assumptions made for a single environment, whereas data-driven approaches based on neural networks are often fragile on extrapolating into the future. In this work, we develop a method of sparse regression dubbed SpReME to discover the major dynamics that underlie multiple environments. Specifically, SpReME shares a sparse structure of ordinary differential equation (ODE) across different environments in common while allowing each environment to keep the coefficients of ODE terms independently. We demonstrate that the proposed model captures the correct dynamics from multiple environments over four different dynamic systems with improved prediction performance.
We present our solution for the EvalRS DataChallenge. The EvalRS DataChallenge aims to build a more realistic recommender system considering accuracy, fairness, and diversity in evaluation. Our proposed system is based on an ensemble between an item-based variational auto-encoder (VAE) and a Bayesian personalized ranking matrix factorization (BPRMF). To mitigate the bias in popularity, we use an item-based VAE for each popularity group with an additional fairness regularization. To make a reasonable recommendation even the predictions are inaccurate, we combine the recommended list of BPRMF and that of item-based VAE. Through the experiments, we demonstrate that the item-based VAE with fairness regularization significantly reduces popularity bias compared to the user-based VAE. The ensemble between the item-based VAE and BPRMF makes the top-1 item similar to the ground truth even the predictions are inaccurate. Finally, we propose a `Coefficient Variance based Fairness' as a novel evaluation metric based on our reflections from the extensive experiments.
Designing a neural network architecture for molecular representation is crucial for AI-driven drug discovery and molecule design. In this work, we propose a new framework for molecular representation learning. Our contribution is threefold: (a) demonstrating the usefulness of incorporating substructures to node-wise features from molecules, (b) designing two branch networks consisting of a transformer and a graph neural network so that the networks fused with asymmetric attention, and (c) not requiring heuristic features and computationally-expensive information from molecules. Using 1.8 million molecules collected from ChEMBL and PubChem database, we pretrain our network to learn a general representation of molecules with minimal supervision. The experimental results show that our pretrained network achieves competitive performance on 11 downstream tasks for molecular property prediction.
We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose latent space consists of a set of diagonal Gaussian distributions. It is known that the set of the diagonal Gaussian distributions with the Fisher information metric forms a product hyperbolic space, which we call a Gaussian manifold. To learn the VAE endowed with the Gaussian manifold, we first propose a pseudo Gaussian manifold normal distribution based on the Kullback-Leibler divergence, a local approximation of the squared Fisher-Rao distance, to define a density over the latent space. With the newly proposed distribution, we introduce geometric transformations at the last and the first of the encoder and the decoder of VAE, respectively to help the transition between the Euclidean and Gaussian manifolds. Through the empirical experiments, we show competitive generalization performance of GM-VAE against other variants of hyperbolic- and Euclidean-VAEs. Our model achieves strong numerical stability, which is a common limitation reported with previous hyperbolic-VAEs.
While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little work has been done on adapting classical GNNs to less-homophilic graphs. Although lacking the ability to work with less-homophilic graphs, classical GNNs still stand out in some properties such as efficiency, simplicity and explainability. We propose a novel graph restructuring method to maximize the benefit of prevalent GNNs with the homophilic assumption. Our contribution is threefold: a) learning the weight of pseudo-eigenvectors for an adaptive spectral clustering that aligns well with known node labels, b) proposing a new homophilic metric that measures how two nodes with the same label are likely to be connected, and c) reconstructing the adjacency matrix based on the result of adaptive spectral clustering to maximize the homophilic scores. The experimental results show that our graph restructuring method can significantly boost the performance of six classical GNNs by an average of 25% on less-homophilic graphs. The boosted performance is comparable to state-of-the-art methods.
Skeleton sequences are compact and lightweight. Numerous skeleton-based action recognizers have been proposed to classify human behaviors. In this work, we aim to incorporate components that are compatible with existing models and further improve their accuracy. To this end, we design two temporal accessories: discrete cosine encoding (DCE) and chronological loss (CRL). DCE facilitates models to analyze motion patterns from the frequency domain and meanwhile alleviates the influence of signal noise. CRL guides networks to explicitly capture the sequence's chronological order. These two components consistently endow many recently-proposed action recognizers with accuracy boosts, achieving new state-of-the-art (SOTA) accuracy on two large benchmark datasets (NTU60 and NTU120).
We consider the problem of machine unlearning to erase a target dataset, which causes an unwanted behavior, from the trained model when the training dataset is not given. Previous works have assumed that the target dataset indicates all the training data imposing the unwanted behavior. However, it is often infeasible to obtain such a complete indication. We hence address a practical scenario of unlearning provided a few samples of target data, so-called few-shot unlearning. To this end, we devise a straightforward framework, including a new model inversion technique to retrieve the training data from the model, followed by filtering out samples similar to the target samples and then relearning. We demonstrate that our method using only a subset of target data can outperform the state-of-the-art methods with a full indication of target data.
Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervised learning framework is often employed to predict the input symbols, where training symbols are used to train the model. 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. To overcome these challenges, we propose a meta-learning-based self-supervised symbol detector named MetaSSD. Our contribution is two-fold: a) meta-learning helps the model adapt to a new channel environment based on experience with various meta-training environments, and b) self-supervised learning helps the model to use relatively less supervision than the previously suggested learning-based detectors. In experiments, MetaSSD outperforms OFDM-MMSE with noisy channel information and shows comparable results with BCJR. Further ablation studies show the necessity of each component in our framework.
We present a rotated hyperbolic wrapped normal distribution (RoWN), a simple yet effective alteration of a hyperbolic wrapped normal distribution (HWN). The HWN expands the domain of probabilistic modeling from Euclidean to hyperbolic space, where a tree can be embedded with arbitrary low distortion in theory. In this work, we analyze the geometric properties of the diagonal HWN, a standard choice of distribution in probabilistic modeling. The analysis shows that the distribution is inappropriate to represent the data points at the same hierarchy level through their angular distance with the same norm in the Poincar\'e disk model. We then empirically verify the presence of limitations of HWN, and show how RoWN, the newly proposed distribution, can alleviate the limitations on various hierarchical datasets, including noisy synthetic binary tree, WordNet, and Atari 2600 Breakout.