An Adaptive Plug-and-Play Network for Few-Shot Learning

Few-shot learning (FSL) requires a model to classify new samples after learning from only a few samples. While remarkable results are achieved in existing methods, the performance of embedding and metrics determines the upper limit of classification accuracy in FSL. The bottleneck is that deep networks and complex metrics tend to induce overfitting in FSL, making it difficult to further improve the performance. Towards this, we propose plug-and-play model-adaptive resizer (MAR) and adaptive similarity metric (ASM) without any other losses. MAR retains high-resolution details to alleviate the overfitting problem caused by data scarcity, and ASM decouples the relationship between different metrics and then fuses them into an advanced one. Extensive experiments show that the proposed method could boost existing methods on two standard dataset and a fine-grained datasets, and achieve state-of-the-art results on mini-ImageNet and tiered-ImageNet.

Embodied Footprints: A Safety-guaranteed Collision Avoidance Model for Numerical Optimization-based Trajectory Planning

Numerical optimization-based methods are among the prevalent trajectory planners for autonomous driving. In a numerical optimization-based planner, the nominal continuous-time trajectory planning problem is discretized into a nonlinear program (NLP) problem with finite constraints imposed on finite collocation points. However, constraint violations between adjacent collocation points may still occur. This study proposes a safety-guaranteed collision-avoidance modeling method to eliminate the collision risks between adjacent collocation points in using numerical optimization-based trajectory planners. A new concept called embodied box is proposed, which is formed by enlarging the rectangular footprint of the ego vehicle. If one can ensure that the embodied boxes at finite collocation points are collide-free, then the ego vehicle's footprint is collide-free at any a moment between adjacent collocation points. We find that the geometric size of an embodied box is a simple function of vehicle velocity and curvature. The proposed theory lays a foundation for numerical optimization-based trajectory planners in autonomous driving.

Denoising and Prompt-Tuning for Multi-Behavior Recommendation

In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e.g., click, add-to-cart, and purchase). Traditional collaborative filtering techniques typically assume that users only have a single type of behavior with items, making it insufficient to utilize complex collaborative signals to learn informative representations and infer actual user preferences. Consequently, some pioneer studies explore modeling multi-behavior heterogeneity to learn better representations and boost the performance of recommendations for a target behavior. However, a large number of auxiliary behaviors (i.e., click and add-to-cart) could introduce irrelevant information to recommenders, which could mislead the target behavior (i.e., purchase) recommendation, rendering two critical challenges: (i) denoising auxiliary behaviors and (ii) bridging the semantic gap between auxiliary and target behaviors. Motivated by the above observation, we propose a novel framework-Denoising and Prompt-Tuning (DPT) with a three-stage learning paradigm to solve the aforementioned challenges. In particular, DPT is equipped with a pattern-enhanced graph encoder in the first stage to learn complex patterns as prior knowledge in a data-driven manner to guide learning informative representation and pinpointing reliable noise for subsequent stages. Accordingly, we adopt different lightweight tuning approaches with effectiveness and efficiency in the following stages to further attenuate the influence of noise and alleviate the semantic gap among multi-typed behaviors. Extensive experiments on two real-world datasets demonstrate the superiority of DPT over a wide range of state-of-the-art methods. The implementation code is available online at https://github.com/zc-97/DPT.

Differentiable modeling to unify machine learning and physical models and advance Geosciences

Process-Based Modeling (PBM) and Machine Learning (ML) are often perceived as distinct paradigms in the geosciences. Here we present differentiable geoscientific modeling as a powerful pathway toward dissolving the perceived barrier between them and ushering in a paradigm shift. For decades, PBM offered benefits in interpretability and physical consistency but struggled to efficiently leverage large datasets. ML methods, especially deep networks, presented strong predictive skills yet lacked the ability to answer specific scientific questions. While various methods have been proposed for ML-physics integration, an important underlying theme -- differentiable modeling -- is not sufficiently recognized. Here we outline the concepts, applicability, and significance of differentiable geoscientific modeling (DG). "Differentiable" refers to accurately and efficiently calculating gradients with respect to model variables, critically enabling the learning of high-dimensional unknown relationships. DG refers to a range of methods connecting varying amounts of prior knowledge to neural networks and training them together, capturing a different scope than physics-guided machine learning and emphasizing first principles. Preliminary evidence suggests DG offers better interpretability and causality than ML, improved generalizability and extrapolation capability, and strong potential for knowledge discovery, while approaching the performance of purely data-driven ML. DG models require less training data while scaling favorably in performance and efficiency with increasing amounts of data. With DG, geoscientists may be better able to frame and investigate questions, test hypotheses, and discover unrecognized linkages.

Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection

Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then apply GNNs to encode edge representations by leveraging the neighborhood structure induced by the fixed subgraph. The prominence of GNNLP methods significantly relies on the adhoc subgraph. Since node connectivity in real-world graphs is complex, one shared subgraph is limited for all edges. Thus, the choices of subgraphs should be personalized to different edges. However, performing personalized subgraph selection is nontrivial since the potential selection space grows exponentially to the scale of edges. Besides, the inference edges are not available during training in link prediction scenarios, so the selection process needs to be inductive. To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP. PS2 is instantiated as a bi-level optimization problem that can be efficiently solved differently. Coupling GNNLP models with PS2, we suggest a brand-new angle towards GNNLP training: by first identifying the optimal subgraphs for edges; and then focusing on training the inference model by using the sampled subgraphs. Comprehensive experiments endorse the effectiveness of our proposed method across various GNNLP backbones (GCN, GraphSage, NGCF, LightGCN, and SEAL) and diverse benchmarks (Planetoid, OGB, and Recommendation datasets). Our code is publicly available at \url{https://github.com/qiaoyu-tan/PS2}

CLIP2GAN: Towards Bridging Text with the Latent Space of GANs

In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and the input latent space of StyleGAN, which is realized by introducing a mapping network. In the training stage, we encode an image with CLIP and map the output feature to a latent code, which is further used to reconstruct the image. In this way, the mapping network is optimized in a self-supervised learning way. In the inference stage, since CLIP can embed both image and text into a shared feature embedding space, we replace CLIP image encoder in the training architecture with CLIP text encoder, while keeping the following mapping network as well as StyleGAN model. As a result, we can flexibly input a text description to generate an image. Moreover, by simply adding mapped text features of an attribute to a mapped CLIP image feature, we can effectively edit the attribute to the image. Extensive experiments demonstrate the superior performance of our proposed CLIP2GAN compared to previous methods.

Music Similarity Calculation of Individual Instrumental Sounds Using Metric Learning

The criteria for measuring music similarity are important for developing a flexible music recommendation system. Some data-driven methods have been proposed to calculate music similarity from only music signals, such as metric learning based on a triplet loss using tag information on each musical piece. However, the resulting music similarity metric usually captures the entire piece of music, i.e., the mixing of various instrumental sound sources, limiting the capability of the music recommendation system, e.g., it is difficult to search for a musical piece containing similar drum sounds. Towards the development of a more flexible music recommendation system, we propose a music similarity calculation method that focuses on individual instrumental sound sources in a musical piece. By fully exploiting the potential of data-driven methods for our proposed method, we employ weakly supervised metric learning to individual instrumental sound source signals without using any tag information, where positive and negative samples in a triplet loss are defined by whether or not they are from the same musical piece. Furthermore, assuming that each instrumental sound source is not always available in practice, we also investigate the effects of using instrumental sound source separation to obtain each source in the proposed method. Experimental results have shown that (1) unique similarity metrics can be learned for individual instrumental sound sources, (2) similarity metrics learned using some instrumental sound sources are possible to lead to more accurate results than that learned using the entire musical piece, (3) the performance degraded when learning with the separated instrumental sounds, and (4) similarity metrics learned by the proposed method well produced results that correspond to perception by human senses.

Coordinating CAV Swarms at Intersections with a Deep Learning Model

Connected and automated vehicles (CAVs) are viewed as a special kind of robots that have the potential to significantly improve the safety and efficiency of traffic. In contrast to many swarm robotics studies that are demonstrated in labs by employing a small number of robots, CAV studies aims to achieve cooperative driving of unceasing robot swarm flows. However, how to get the optimal passing order of such robot swarm flows even for a signal-free intersection is an NP-hard problem (specifically, enumerating based algorithm takes days to find the optimal solution to a 20-CAV scenario). Here, we introduce a novel cooperative driving algorithm (AlphaOrder) that combines offline deep learning and online tree searching to find a near-optimal passing order in real-time. AlphaOrder builds a pointer network model from solved scenarios and generates near-optimal passing orders instantaneously for new scenarios. Furthermore, our approach provides a general approach to managing preemptive resource sharing between swarm robotics (e.g., scheduling multiple automated guided vehicles (AGVs) and unmanned aerial vehicles (UAVs) at conflicting areas

Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system

Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR). In this work, we propose a phonetic-assisted multi-target units (PMU) modeling approach, to enhance the Conformer-Transducer ASR system in a progressive representation learning manner. Specifically, PMU first uses the pronunciation-assisted subword modeling (PASM) and byte pair encoding (BPE) to produce phonetic-induced and text-induced target units separately; Then, three new frameworks are investigated to enhance the acoustic encoder, including a basic PMU, a paraCTC and a pcaCTC, they integrate the PASM and BPE units at different levels for CTC and transducer multi-task training. Experiments on both LibriSpeech and accented ASR tasks show that, the proposed PMU significantly outperforms the conventional BPE, it reduces the WER of LibriSpeech clean, other, and six accented ASR testsets by relative 12.7%, 6.0% and 7.7%, respectively.

DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion

Two-view structure from motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM (vSLAM). Many existing end-to-end learning-based methods usually formulate it as a brute regression problem. However, the inadequate utilization of traditional geometry model makes the model not robust in unseen environments. To improve the generalization capability and robustness of end-to-end two-view SfM network, we formulate the two-view SfM problem as a maximum likelihood estimation (MLE) and solve it with the proposed framework, denoted as DeepMLE. First, we propose to take the deep multi-scale correlation maps to depict the visual similarities of 2D image matches decided by ego-motion. In addition, in order to increase the robustness of our framework, we formulate the likelihood function of the correlations of 2D image matches as a Gaussian and Uniform mixture distribution which takes the uncertainty caused by illumination changes, image noise and moving objects into account. Meanwhile, an uncertainty prediction module is presented to predict the pixel-wise distribution parameters. Finally, we iteratively refine the depth and relative camera pose using the gradient-like information to maximize the likelihood function of the correlations. Extensive experimental results on several datasets prove that our method significantly outperforms the state-of-the-art end-to-end two-view SfM approaches in accuracy and generalization capability.