Empathetic response from the therapist is key to the success of clinical psychotherapy, especially motivational interviewing. Previous work on computational modelling of empathy in motivational interviewing has focused on offline, session-level assessment of therapist empathy, where empathy captures all efforts that the therapist makes to understand the client's perspective and convey that understanding to the client. In this position paper, we propose a novel task of turn-level detection of client need for empathy. Concretely, we propose to leverage pre-trained language models and empathy-related general conversation corpora in a unique labeller-detector framework, where the labeller automatically annotates a motivational interviewing conversation corpus with empathy labels to train the detector that determines the need for therapist empathy. We also lay out our strategies of extending the detector with additional-input and multi-task setups to improve its detection and explainability.
We consider the natural problem of learning a ReLU network from queries, which was recently remotivated by model extraction attacks. In this work, we present a polynomial-time algorithm that can learn a depth-two ReLU network from queries under mild general position assumptions. We also present a polynomial-time algorithm that, under mild general position assumptions, can learn a rich class of depth-three ReLU networks from queries. For instance, it can learn most networks where the number of first layer neurons is smaller than the dimension and the number of second layer neurons. These two results substantially improve state-of-the-art: Until our work, polynomial-time algorithms were only shown to learn from queries depth-two networks under the assumption that either the underlying distribution is Gaussian (Chen et al. (2021)) or that the weights matrix rows are linearly independent (Milli et al. (2019)). For depth three or more, there were no known poly-time results.
Real-time visual localization of needles is necessary for various surgical applications, including surgical automation and visual feedback. In this study we investigate localization and autonomous robotic control of needles in the context of our magneto-suturing system. Our system holds the potential for surgical manipulation with the benefit of minimal invasiveness and reduced patient side effects. However, the non-linear magnetic fields produce unintuitive forces and demand delicate position-based control that exceeds the capabilities of direct human manipulation. This makes automatic needle localization a necessity. Our localization method combines neural network-based segmentation and classical techniques, and we are able to consistently locate our needle with 0.73 mm RMS error in clean environments and 2.72 mm RMS error in challenging environments with blood and occlusion. The average localization RMS error is 2.16 mm for all environments we used in the experiments. We combine this localization method with our closed-loop feedback control system to demonstrate the further applicability of localization to autonomous control. Our needle is able to follow a running suture path in (1) no blood, no tissue; (2) heavy blood, no tissue; (3) no blood, with tissue; and (4) heavy blood, with tissue environments. The tip position tracking error ranges from 2.6 mm to 3.7 mm RMS, opening the door towards autonomous suturing tasks.
In this position paper, we argue for the need to investigate if and how gender stereotypes manifest in search and recommender systems.As a starting point, we particularly focus on how these systems may propagate and reinforce gender stereotypes through their results in learning environments, a context where teachers and children in their formative stage regularly interact with these systems. We provide motivating examples supporting our concerns and outline an agenda to support future research addressing the phenomena.
All hand-object interaction is controlled by forces that the two bodies exert on each other, but little work has been done in modeling these underlying forces when doing pose and contact estimation from RGB/RGB-D data. Given the pose of the hand and object from any pose estimation system, we propose an end-to-end differentiable model that refines pose estimates by learning the forces experienced by the object at each vertex in its mesh. By matching the learned net force to an estimate of net force based on finite differences of position, this model is able to find forces that accurately describe the movement of the object, while resolving issues like mesh interpenetration and lack of contact. Evaluating on the ContactPose dataset, we show this model successfully corrects poses and finds contact maps that better match the ground truth, despite not using any RGB or depth image data.
X-ray Ptychography is an advanced computational microscopy technique which is delivering exceptionally detailed quantitative imaging of biological and nanotechnology specimens. However coarse parametrisation in propagation distance, position errors and partial coherence frequently menaces the experiment viability. In this work we formally introduced these actors, solving the whole reconstruction as an optimisation problem. A modern Deep Learning framework is used to correct autonomously the setup incoherences, thus improving the quality of a ptychography reconstruction. Automatic procedures are indeed crucial to reduce the time for a reliable analysis, which has a significant impact on all the fields that use this kind of microscopy. We implemented our algorithm in our software framework, SciComPty, releasing it as open-source. We tested our system on both synthetic datasets and also on real data acquired at the TwinMic beamline of the Elettra synchrotron facility.
We consider the problem of spatial signal design for multipath-assisted mmWave positioning under limited prior knowledge on the user's location and clock bias. We propose an optimal robust design and, based on the low-dimensional precoder structure under perfect prior knowledge, a codebook-based heuristic design with optimized beam power allocation. Through numerical results, we characterize different position-error-bound (PEB) regimes with respect to clock bias uncertainty and show that the proposed low-complexity codebook-based designs outperform the conventional directional beam codebook and achieve near-optimal PEB performance for both analog and digital architectures.
Recently, program autotuning has become very popular especially in embedded systems, when we have limited resources such as computing power and memory where these systems run generally time-critical applications. Compiler optimization space gradually expands with the renewed compiler options and inclusion of new architectures. These advancements bring autotuning even more important position. In this paper, we introduced Flag Optimization with Genetic Algorithm (FOGA) as an autotuning solution for GCC flag optimization. FOGA has two main advantages over the other autotuning approaches: the first one is the hyperparameter tuning of the genetic algorithm (GA), the second one is the maximum iteration parameter to stop when no further improvement occurs. We demonstrated remarkable speedup in the execution time of C++ source codes with the help of optimization flags provided by FOGA when compared to the state of the art framework OpenTuner.
Radio Map Prediction (RMP), aiming at estimating coverage of radio wave, has been widely recognized as an enabling technology for improving radio spectrum efficiency. However, fast and reliable radio map prediction can be very challenging due to the complicated interaction between radio waves and the environment. In this paper, a novel Transformer based deep learning model termed as RadioNet is proposed for radio map prediction in urban scenarios. In addition, a novel Grid Embedding technique is proposed to substitute the original Position Embedding in Transformer to better anchor the relative position of the radiation source, destination and environment. The effectiveness of proposed method is verified on an urban radio wave propagation dataset. Compared with the SOTA model on RMP task, RadioNet reduces the validation loss by 27.3\%, improves the prediction reliability from 90.9\% to 98.9\%. The prediction speed is increased by 4 orders of magnitude, when compared with ray-tracing based method. We believe that the proposed method will be beneficial to high-efficiency wireless communication, real-time radio visualization, and even high-speed image rendering.
It is common for video-on-demand and music streaming services to adopt a user interface composed of several recommendation lists, i.e. widgets or swipeable carousels, each generated according to a specific criterion or algorithm (e.g. most recent, top popular, recommended for you, editors' choice, etc.). Selecting the appropriate combination of carousel has significant impact on user satisfaction. A crucial aspect of this user interface is that to measure the relevance a new carousel for the user it is not sufficient to account solely for its individual quality. Instead, it should be considered that other carousels will already be present in the interface. This is not considered by traditional evaluation protocols for recommenders systems, in which each carousel is evaluated in isolation, regardless of (i) which other carousels are displayed to the user and (ii) the relative position of the carousel with respect to other carousels. Hence, we propose a two-dimensional evaluation protocol for a carousel setting that will measure the quality of a recommendation carousel based on how much it improves upon the quality of an already available set of carousels. Our evaluation protocol takes into account also the position bias, i.e. users do not explore the carousels sequentially, but rather concentrate on the top-left corner of the screen. We report experiments on the movie domain and notice that under a carousel setting the definition of which criteria has to be preferred to generate a list of recommended items changes with respect to what is commonly understood.
Scene flow in 3D point clouds plays an important role in understanding dynamic environments. Although significant advances have been made by deep neural networks, the performance is far from satisfactory as only per-point translational motion is considered, neglecting the constraints of the rigid motion in local regions. To address the issue, we propose to introduce the motion consistency to force the smoothness among neighboring points. In addition, constraints on the rigidity of the local transformation are also added by sharing unique rigid motion parameters for all points within each local region. To this end, a high-order CRFs based relation module (Con-HCRFs) is deployed to explore both point-wise smoothness and region-wise rigidity. To empower the CRFs to have a discriminative unary term, we also introduce a position-aware flow estimation module to be incorporated into the Con-HCRFs. Comprehensive experiments on FlyingThings3D and KITTI show that our proposed framework (HCRF-Flow) achieves state-of-the-art performance and significantly outperforms previous approaches substantially.
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.
Multiple studies have shown that Transformers are remarkably robust to pruning. Contrary to this received wisdom, we demonstrate that pre-trained Transformer encoders are surprisingly fragile to the removal of a very small number of features in the layer outputs (<0.0001% of model weights). In case of BERT and other pre-trained encoder Transformers, the affected component is the scaling factors and biases in the LayerNorm. The outliers are high-magnitude normalization parameters that emerge early in pre-training and show up consistently in the same dimensional position throughout the model. We show that disabling them significantly degrades both the MLM loss and the downstream task performance. This effect is observed across several BERT-family models and other popular pre-trained Transformer architectures, including BART, XLNet and ELECTRA; we also show a similar effect in GPT-2.
A commonly-cited reason for the poor performance of automatic chord estimation (ACE) systems within music information retrieval (MIR) is that non-chord tones (i.e., notes outside the supporting harmony) contribute to error during the labeling process. Despite the prevalence of machine learning approaches in MIR, there are cases where alternative approaches provide a simpler alternative while allowing for insights into musicological practices. In this project, we present a statistical model for predicting chord tones based on music theory rules. Our model is currently focused on predicting chord tones in classical music, since composition in this style is highly constrained, theoretically making the placement of chord tones highly predictable. Indeed, music theorists have labeling systems for every variety of non-chord tone, primarily classified by the note's metric position and intervals of approach and departure. Using metric position, duration, and melodic intervals as predictors, we build a statistical model for predicting chord tones using the TAVERN dataset. While our probabilistic approach is similar to other efforts in the domain of automatic harmonic analysis, our focus is on melodic reduction rather than predicting harmony. However, we hope to pursue applications for ACE in the future. Finally, we implement our melody reduction model using an existing symbolic visualization tool, to assist with melody reduction and non-chord tone identification for computational musicology researchers and music theorists.
Unbiased Learning to Rank (ULTR) studies the problem of learning a ranking function based on biased user interactions. In this framework, ULTR algorithms have to rely on a large amount of user data that are collected, stored, and aggregated by central servers. In this paper, we consider an on-device search setting, where users search against their personal corpora on their local devices, and the goal is to learn a ranking function from biased user interactions. Due to privacy constraints, users' queries, personal documents, results lists, and raw interaction data will not leave their devices, and ULTR has to be carried out via Federated Learning (FL). Directly applying existing ULTR algorithms on users' devices could suffer from insufficient training data due to the limited amount of local interactions. To address this problem, we propose the FedIPS algorithm, which learns from user interactions on-device under the coordination of a central server and uses click propensities to remove the position bias in user interactions. Our evaluation of FedIPS on the Yahoo and Istella datasets shows that FedIPS is robust over a range of position biases.
We discuss a new neural network-based direction of arrival estimation scheme that tackles the estimation task as a multidimensional classification problem. The proposed estimator uses a classification chain with as many stages as the number of sources. Each stage is a multiclass classification network that estimates the position of one of the sources. This approach can be interpreted as the approximation of a successive evaluation of the maximum a posteriori estimator. By means of simulations for fully sampled antenna arrays and systems with subarray sampling, we show that it is able to outperform existing estimation techniques in terms of accuracy, while maintaining a very low computational complexity.
Learning node representations that incorporate information from graph structure benefits wide range of tasks on graph. The majority of existing graph neural networks (GNNs) have limited power in capturing position information for a given node. The idea of positioning nodes with selected anchors has been exploited, yet mainly relying on explicit labeling of distance information. Here we propose Graph Inference Representation (GIR), an anchor based GNN model encoding path information related to pre-selected anchors for each node. Abilities to get position-aware embeddings are theoretically and experimentally investigated on GIR and its core variants. Further, the complementarity between GIRs and typical GNNs is demonstrated. We show that GIRs get outperformed results in position-aware scenarios, and performances on typical GNNs could be improved by fusing GIR embeddings.
This paper presents a mathematic dynamic model of a quadrotor unmanned aerial vehicle (QUAV) by using the symbolic regression approach and then proposes a hierarchical control scheme for trajectory tracking. The symbolic regression approach is capable of constructing analytical quadrotor dynamic equations only through the collected data, which relieves the burden of first principle modeling. To facilitate position tracking control of a QUAV, the design of controller can be decomposed into two parts: a proportional-integral controller for the position subsystem is first designed to obtain the desired horizontal position and the backstepping method for the attitude subsystem is developed to ensure that the Euler angles and the altitude can fast converge to the reference values. The effectiveness is verified through experiments on a benchmark multicopter simulator.
To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33,600 HD frames in various scenarios. Notably, we annotate 20,800 people trajectories with 4.8 million heads and several video-level attributes. Meanwhile, we design the Space-Time Neighbor-Aware Network (STNNet) as a strong baseline to solve object detection, tracking and counting jointly in dense crowds. STNNet is formed by the feature extraction module, followed by the density map estimation heads, and localization and association subnets. To exploit the context information of neighboring objects, we design the neighboring context loss to guide the association subnet training, which enforces consistent relative position of nearby objects in temporal domain. Extensive experiments on our DroneCrowd dataset demonstrate that STNNet performs favorably against the state-of-the-arts.
In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for the improvement of about +1 BLEU across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.