Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models

Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and analyses of multilingual models have employed correlational methods that are confounded by the choice of probing tasks. In this study, we causally probe multilingual language models (XGLM and multilingual BERT) as well as monolingual BERT-based models across various languages; we do this by performing counterfactual perturbations on neuron activations and observing the effect on models' subject-verb agreement probabilities. We observe where in the model and to what extent syntactic agreement is encoded in each language. We find significant neuron overlap across languages in autoregressive multilingual language models, but not masked language models. We also find two distinct layer-wise effect patterns and two distinct sets of neurons used for syntactic agreement, depending on whether the subject and verb are separated by other tokens. Finally, we find that behavioral analyses of language models are likely underestimating how sensitive masked language models are to syntactic information.

Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging. Although the recurrent structure utilized in current advances helps to capture local dynamics, modeling only state transitions without an explicit understanding of environmental context limits the generalization ability of the dynamics model. To address this issue, we propose a Prototypical Context-Aware Dynamics (ProtoCAD) model, which captures the local dynamics by time consistent latent context and enables dynamics generalization in high-dimensional control tasks. ProtoCAD extracts useful contextual information with the help of the prototypes clustered over batch and benefits model-based RL in two folds: 1) It utilizes a temporally consistent prototypical regularizer that encourages the prototype assignments produced for different time parts of the same latent trajectory to be temporally consistent instead of comparing the features; 2) A context representation is designed which combines both the projection embedding of latent states and aggregated prototypes and can significantly improve the dynamics generalization ability. Extensive experiments show that ProtoCAD surpasses existing methods in terms of dynamics generalization. Compared with the recurrent-based model RSSM, ProtoCAD delivers 13.2% and 26.7% better mean and median performance across all dynamics generalization tasks.

Inversion-Based Creativity Transfer with Diffusion Models

In this paper, we introduce the task of "Creativity Transfer". The artistic creativity within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes including semantic elements, object shape, etc. Previous arbitrary example-guided artistic image generation methods (e.g., style transfer) often fail to control shape changes or convey semantic elements. The pre-trained text-to-image synthesis diffusion probabilistic models have achieved remarkable quality, but they often require extensive textual descriptions to accurately portray attributes of a particular painting. We believe that the uniqueness of an artwork lies precisely in the fact that it cannot be adequately explained with normal language. Our key idea is to learn artistic creativity directly from a single painting and then guide the synthesis without providing complex textual descriptions. Specifically, we assume creativity as a learnable textual description of a painting. We propose an attention-based inversion method, which can efficiently and accurately learn the holistic and detailed information of an image, thus capturing the complete artistic creativity of a painting. We demonstrate the quality and efficiency of our method on numerous paintings of various artists and styles. Code and models are available at https://github.com/zyxElsa/creativity-transfer.

ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation

Vision transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships. Constrained by data hungry nature of transformers and limited labelled data most transformer-based models for audio tasks are finetuned from ImageNet pretrained models, despite the huge gap between the natural images domain and audio domain. This has motivated the research in self-supervised pretraining of audio transformers, which reduces the dependency on large amounts of labeled data and focuses on extracting concise representation of the audio spectrograms. In this paper, we propose ASiT, a novel self-supervised transformer for general audio representations that captures local and global contextual information employing group masked model learning and self-distillation. We evaluate our pretrained models on both audio and speech classification tasks including audio event classification, keyword spotting, and speaker identification. We further conduct comprehensive ablation studies, including evaluations of different pretraining strategies. The proposed ASiT framework significantly boosts the performance on all tasks and sets a new state-of-the-art performance on five audio and speech classification tasks, outperforming recent methods, including the approaches that use additional datasets for pretraining. The code and pretrained weights will be made publicly available for the scientific community.

DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracing

Knowledge tracing aims to trace students' evolving knowledge states by predicting their future performance on concept-related exercises. Recently, some graph-based models have been developed to incorporate the relationships between exercises to improve knowledge tracing, but only a single type of relationship information is generally explored. In this paper, we present a novel Dual Graph Ensemble learning method for Knowledge Tracing (DGEKT), which establishes a dual graph structure of students' learning interactions to capture the heterogeneous exercise-concept associations and interaction transitions by hypergraph modeling and directed graph modeling, respectively. To ensemble the dual graph models, we introduce the technique of online knowledge distillation, due to the fact that although the knowledge tracing model is expected to predict students' responses to the exercises related to different concepts, it is optimized merely with respect to the prediction accuracy on a single exercise at each step. With online knowledge distillation, the dual graph models are adaptively combined to form a stronger teacher model, which in turn provides its predictions on all exercises as extra supervision for better modeling ability. In the experiments, we compare DGEKT against eight knowledge tracing baselines on three benchmark datasets, and the results demonstrate that DGEKT achieves state-of-the-art performance.

An Open Case-based Reasoning Framework for Personalized On-board Driving Assistance in Risk Scenarios

Driver reaction is of vital importance in risk scenarios. Drivers can take correct evasive maneuver at proper cushion time to avoid the potential traffic crashes, but this reaction process is highly experience-dependent and requires various levels of driving skills. To improve driving safety and avoid the traffic accidents, it is necessary to provide all road drivers with on-board driving assistance. This study explores the plausibility of case-based reasoning (CBR) as the inference paradigm underlying the choice of personalized crash evasive maneuvers and the cushion time, by leveraging the wealthy of human driving experience from the steady stream of traffic cases, which have been rarely explored in previous studies. To this end, in this paper, we propose an open evolving framework for generating personalized on-board driving assistance. In particular, we present the FFMTE model with high performance to model the traffic events and build the case database; A tailored CBR-based method is then proposed to retrieve, reuse and revise the existing cases to generate the assistance. We take the 100-Car Naturalistic Driving Study dataset as an example to build and test our framework; the experiments show reasonable results, providing the drivers with valuable evasive information to avoid the potential crashes in different scenarios.

3-D Positioning and Resource Allocation for Multi-UAV Base Stations Under Blockage-Aware Channel Model

In this paper, we propose to deploy multiple unmanned aerial vehicle (UAV) mounted base stations to serve ground users in outdoor environments with obstacles. In particular, the geographic information is employed to capture the blockage effects for air-to-ground (A2G) links caused by buildings, and a realistic blockage-aware A2G channel model is proposed to characterize the continuous variation of the channels at different locations. Based on the proposed channel model, we formulate the joint optimization problem of UAV three-dimensional (3-D) positioning and resource allocation, by power allocation, user association, and subcarrier allocation, to maximize the minimum achievable rate among users. To solve this non-convex combinatorial programming problem, we introduce a penalty term to relax it and develop a suboptimal solution via a penalty-based double-loop iterative optimization framework. The inner loop solves the penalized problem by employing the block successive convex approximation (BSCA) technique, where the UAV positioning and resource allocation are alternately optimized in each iteration. The outer loop aims to obtain proper penalty multipliers to ensure the solution of the penalized problem converges to that of the original problem. Simulation results demonstrate the superiority of the proposed algorithm over other benchmark schemes in terms of the minimum achievable rate.

Zero Forcing Uplink Detection through Large-Scale RIS: System Performance and Phase Shift Design

A multiple-input multiple-output wireless communication system is analytically studied, which operates with the aid of a large-scale reconfigurable intelligent surface (LRIS). LRIS is equipped with multiple passive elements with discrete phase adjustment capabilities, and independent Rician fading conditions are assumed for both the transmitter-to-LRIS and LRIS-to-receiver links. A direct transceiver link is also considered which is modeled by Rayleigh fading distribution. The system performance is analytically studied when the linear yet efficient zero-forcing detection is implemented at the receiver. In particular, the outage performance is derived in closed-form expression for different system configuration setups with regards to the available channel state information (CSI) at the receiver. In fact, the case of both perfect and imperfect CSI is analyzed. Also, an efficient phase shift design approach at LRIS is introduced, which is linear on the number of passive elements and receive antennas. The proposed phase shift design can be applied on two different modes of operation; namely, when the system strives to adapt either on the instantaneous or statistical CSI. Finally, some impactful engineering insights are provided, such as how the channel fading conditions, CSI, discrete phase shift resolution, and volume of antenna/LRIS element arrays impact on the overall system performance.

Exploring Explainability Methods for Graph Neural Networks

With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper, we demonstrate the applicability of popular explainability approaches on Graph Attention Networks (GAT) for a graph-based super-pixel image classification task. We assess the qualitative and quantitative performance of these techniques on three different datasets and describe our findings. The results shed a fresh light on the notion of explainability in GNNs, particularly GATs.

Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective

Knowledge graph completion (KGC) aims to infer missing knowledge triples based on known facts in a knowledge graph. Current KGC research mostly follows an entity ranking protocol, wherein the effectiveness is measured by the predicted rank of a masked entity in a test triple. The overall performance is then given by a micro(-average) metric over all individual answer entities. Due to the incomplete nature of the large-scale knowledge bases, such an entity ranking setting is likely affected by unlabelled top-ranked positive examples, raising questions on whether the current evaluation protocol is sufficient to guarantee a fair comparison of KGC systems. To this end, this paper presents a systematic study on whether and how the label sparsity affects the current KGC evaluation with the popular micro metrics. Specifically, inspired by the TREC paradigm for large-scale information retrieval (IR) experimentation, we create a relatively "complete" judgment set based on a sample from the popular FB15k-237 dataset following the TREC pooling method. According to our analysis, it comes as a surprise that switching from the original labels to our "complete" labels results in a drastic change of system ranking of a variety of 13 popular KGC models in terms of micro metrics. Further investigation indicates that the IR-like macro(-average) metrics are more stable and discriminative under different settings, meanwhile, less affected by label sparsity. Thus, for KGC evaluation, we recommend conducting TREC-style pooling to balance between human efforts and label completeness, and reporting also the IR-like macro metrics to reflect the ranking nature of the KGC task.