Shiv Shankar

Shiv Shankar, Laure Thompson, Madalina Fiterau · princeton

Integration of multimodal information from various sources has been shown to boost the performance of machine learning models and thus has received increased attention in recent years. Often such models use deep modality-specific networks to obtain unimodal features which are combined to obtain "late-fusion" representations. However, these designs run the risk of information loss in the respective unimodal pipelines. On the other hand, "early-fusion" methodologies, which combine features early, suffer from the problems associated with feature heterogeneity and high sample complexity. In this work, we present an iterative representation refinement approach, called Progressive Fusion, which mitigates the issues with late fusion representations. Our model-agnostic technique introduces backward connections that make late stage fused representations available to early layers, improving the expressiveness of the representations at those stages, while retaining the advantages of late fusion designs. We test Progressive Fusion on tasks including affective sentiment detection, multimedia analysis, and time series fusion with different models, demonstrating its versatility. We show that our approach consistently improves performance, for instance attaining a 5% reduction in MSE and 40% improvement in robustness on multimodal time series prediction.

Yash Chandak, Shiv Shankar, Nathaniel D. Bastian et al.

Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes due to external factors (passive non-stationarity), changes induced by interactions with the system itself (active non-stationarity), or both (hybrid non-stationarity). In this work, we take the first steps towards the fundamental challenge of on-policy and off-policy evaluation amidst structured changes due to active, passive, or hybrid non-stationarity. Towards this goal, we make a higher-order stationarity assumption such that non-stationarity results in changes over time, but the way changes happen is fixed. We propose, OPEN, an algorithm that uses a double application of counterfactual reasoning and a novel importance-weighted instrument-variable regression to obtain both a lower bias and a lower variance estimate of the structure in the changes of a policy's past performances. Finally, we show promising results on how OPEN can be used to predict future performances for several domains inspired by real-world applications that exhibit non-stationarity.

Shiv Shankar, Ritwik Sinha, Saayan Mitra et al.

Consider two brands that want to jointly test alternate web experiences for their customers with an A/B test. Such collaborative tests are today enabled using \textit{third-party cookies}, where each brand has information on the identity of visitors to another website. With the imminent elimination of third-party cookies, such A/B tests will become untenable. We propose a two-stage experimental design, where the two brands only need to agree on high-level aggregate parameters of the experiment to test the alternate experiences. Our design respects the privacy of customers. We propose an estimater of the Average Treatment Effect (ATE), show that it is unbiased and theoretically compute its variance. Our demonstration describes how a marketer for a brand can design such an experiment and analyze the results. On real and simulated data, we show that the approach provides valid estimate of the ATE with low variance and is robust to the proportion of visitors overlapping across the brands.

Yash Chandak, Shiv Shankar, Venkata Gandikota et al.

We propose a first-order method for convex optimization, where instead of being restricted to the gradient from a single parameter, gradients from multiple parameters can be used during each step of gradient descent. This setup is particularly useful when a few processors are available that can be used in parallel for optimization. Our method uses gradients from multiple parameters in synergy to update these parameters together towards the optima. While doing so, it is ensured that the computational and memory complexity is of the same order as that of gradient descent. Empirical results demonstrate that even using gradients from as low as \textit{two} parameters, our method can often obtain significant acceleration and provide robustness to hyper-parameter settings. We remark that the primary goal of this work is less theoretical, and is instead aimed at exploring the understudied case of using multiple gradients during each step of optimization.

Shiv Shankar, Vihari Piratla

Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of standard losses. When the objective aligns well with the evaluation metric, this is not a major issue. However when dealing with complex structured outputs, the ideal objective can be hard to optimize and the efficacy of usual objectives as a proxy for the true objective can be questionable. In this work, we argue that the existing inference network based structure prediction methods ( Tu and Gimpel 2018; Tu, Pang, and Gimpel 2020) are indirectly learning to optimize a dynamic loss objective parameterized by the energy model. We then explore using implicit-gradient based technique to learn the corresponding dynamic objectives. Our experiments show that implicitly learning a dynamic loss landscape is an effective method for improving model performance in structure prediction.

Yash Chandak, Shiv Shankar, Vasilis Syrgkanis et al.

Indirect experiments provide a valuable framework for estimating treatment effects in situations where conducting randomized control trials (RCTs) is impractical or unethical. Unlike RCTs, indirect experiments estimate treatment effects by leveraging (conditional) instrumental variables, enabling estimation through encouragement and recommendation rather than strict treatment assignment. However, the sample efficiency of such estimators depends not only on the inherent variability in outcomes but also on the varying compliance levels of users with the instrumental variables and the choice of estimator being used, especially when dealing with numerous instrumental variables. While adaptive experiment design has a rich literature for direct experiments, in this paper we take the initial steps towards enhancing sample efficiency for indirect experiments by adaptively designing a data collection policy over instrumental variables. Our main contribution is a practical computational procedure that utilizes influence functions to search for an optimal data collection policy, minimizing the mean-squared error of the desired (non-linear) estimator. Through experiments conducted in various domains inspired by real-world applications, we showcase how our method can significantly improve the sample efficiency of indirect experiments.

Shiv Shankar, Ritwik Sinha, Yash Chandak et al.

A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control the spread of an epidemic. In such settings, the SUTVA assumption for randomized-controlled trials is violated due to network interference, or spill-over effects, as treatments to group A can potentially also affect the control group B. When the underlying social network is known exactly, prior works have demonstrated how to conduct A/B tests adequately to estimate the global average treatment effect (GATE). However, in practice, it is often impossible to obtain knowledge about the exact underlying network. In this paper, we present UNITE: a novel estimator that relax this assumption and can identify GATE while only relying on knowledge of the superset of neighbors for any subject in the graph. Through theoretical analysis and extensive experiments, we show that the proposed approach performs better in comparison to standard estimators.

Shiv Shankar, Tomas Geffner

Flow matching models typically use linear interpolants to define the forward/noise addition process. This, together with the independent coupling between noise and target distributions, yields a vector field which is often non-straight. Such curved fields lead to a slow inference/generation process. In this work, we propose to learn flexible (potentially curved) interpolants in order to learn straight vector fields to enable faster generation. We formulate this via a multi-level optimization problem and propose an efficient approximate procedure to solve it. Our framework provides an end-to-end and simulation-free optimization procedure, which can be leveraged to learn straight line generative trajectories.

Shiv Shankar

Information integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different sensory perceptive fields to interact with the environment and each other. Recent work in deep fusion models via neural networks has led to substantial improvements over unimodal approaches in areas like speech recognition, emotion recognition and analysis, captioning and image description. However, such research has mostly focused on architectural changes allowing for fusion of different modalities while keeping the model complexity manageable. Inspired by recent neuroscience ideas about multisensory integration and processing, we investigate the effect of synergy maximizing loss functions. Experiments on multimodal sentiment analysis tasks: CMU-MOSI and CMU-MOSEI with different models show that our approach provides a consistent performance boost.

Shiv Shankar

Learning distributions over graph-structured data is a challenging task with many applications in biology and chemistry. In this work we use an energy-based model (EBM) based on multi-channel graph neural networks (GNN) to learn permutation invariant unnormalized density functions on graphs. Unlike standard EBM training methods our approach is to learn the model via minimizing adversarial stein discrepancy. Samples from the model can be obtained via Langevin dynamics based MCMC. We find that this approach achieves competitive results on graph generation compared to benchmark models.

Shiv Shankar, Daniel Sheldon

Field observations form the basis of many scientific studies, especially in ecological and social sciences. Despite efforts to conduct such surveys in a standardized way, observations can be prone to systematic measurement errors. The removal of systematic variability introduced by the observation process, if possible, can greatly increase the value of this data. Existing non-parametric techniques for correcting such errors assume linear additive noise models. This leads to biased estimates when applied to generalized linear models (GLM). We present an approach based on residual functions to address this limitation. We then demonstrate its effectiveness on synthetic data and show it reduces systematic detection variability in moth surveys.

Yash Chandak, Shiv Shankar, Philip S. Thomas

Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before deployment, to ensure that the policy will behave as desired. Prior works have studied high-confidence off-policy estimation of the expected return, however, high-confidence off-policy estimation of the variance of returns can be equally critical for high-risk applications. In this paper, we tackle the previously open problem of estimating and bounding, with high confidence, the variance of returns from off-policy data

Shiv Shankar, Don Towsley

The development of Graph Neural Networks (GNNs) has led to great progress in machine learning on graph-structured data. These networks operate via diffusing information across the graph nodes while capturing the structure of the graph. Recently there has also seen tremendous progress in quantum computing techniques. In this work, we explore applications of multi-particle quantum walks on diffusing information across graphs. Our model is based on learning the operators that govern the dynamics of quantum random walkers on graphs. We demonstrate the effectiveness of our method on classification and regression tasks.

Shiv Shankar, Daniel Sheldon, Tao Sun et al.

Many ecological studies and conservation policies are based on field observations of species, which can be affected by systematic variability introduced by the observation process. A recently introduced causal modeling technique called 'half-sibling regression' can detect and correct for systematic errors in measurements of multiple independent random variables. However, it will remove intrinsic variability if the variables are dependent, and therefore does not apply to many situations, including modeling of species counts that are controlled by common causes. We present a technique called 'three-quarter sibling regression' to partially overcome this limitation. It can filter the effect of systematic noise when the latent variables have observed common causes. We provide theoretical justification of this approach, demonstrate its effectiveness on synthetic data, and show that it reduces systematic detection variability due to moon brightness in moth surveys.

Vihari Piratla, Shiv Shankar

Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared between the original and augmented counterparts. However, we show that is not the case even for the best augmentation technique. In this work, we take a Domain Generalization viewpoint of augmentation based methods. This new perspective allowed for probing overfitting and delineating avenues for improvement. Our exploration with the state-of-art augmentation method provides evidence that the learned representations are not as robust even towards distortions used during training. This suggests evidence for the untapped potential of augmented examples.

Yash Chandak, Georgios Theocharous, Shiv Shankar et al.

Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this assumption is violated, and using existing algorithms may result in a performance lag. To proactively search for a good future policy, we present a policy gradient algorithm that maximizes a forecast of future performance. This forecast is obtained by fitting a curve to the counter-factual estimates of policy performance over time, without explicitly modeling the underlying non-stationarity. The resulting algorithm amounts to a non-uniform reweighting of past data, and we observe that minimizing performance over some of the data from past episodes can be beneficial when searching for a policy that maximizes future performance. We show that our algorithm, called Prognosticator, is more robust to non-stationarity than two online adaptation techniques, on three simulated problems motivated by real-world applications.

MohamadAli Torkamani, Shiv Shankar, Amirmohammad Rooshenas et al.

Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact network capable of achieving comparable, if not superior, performance when is compared to much larger networks.

MohamadAli Torkamani, Phillip Wallis, Shiv Shankar et al.

Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact network capable of achieving comparable, if not superior, performance when is compared to much larger networks.

Shiv Shankar, Vihari Piratla, Soumen Chakrabarti et al.

We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or unlabeled data, or domain features in the new domain. Most existing domain adaptation methods attempt to erase domain signals using techniques like domain adversarial training. In contrast, CROSSGRAD is free to use domain signals for predicting labels, if it can prevent overfitting on training domains. We conceptualize the task in a Bayesian setting, in which a sampling step is implemented as data augmentation, based on domain-guided perturbations of input instances. CROSSGRAD parallelly trains a label and a domain classifier on examples perturbed by loss gradients of each other's objectives. This enables us to directly perturb inputs, without separating and re-mixing domain signals while making various distributional assumptions. Empirical evaluation on three different applications where this setting is natural establishes that (1) domain-guided perturbation provides consistently better generalization to unseen domains, compared to generic instance perturbation methods, and that (2) data augmentation is a more stable and accurate method than domain adversarial training.

Shiv Shankar, Sunita Sarawagi

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in classification models. LMNs organize the memory with classes as the primary key.The memory acts as a second boosted stage following a regular neural network thereby allowing the memory and the primary network to play complementary roles. Unlike existing MANNs that write to memory for every instance and use LRU based memory replacement, LMNs write only for instances with non-zero loss and use label-based memory replacement. We demonstrate significant accuracy gains on various tasks including word-modelling and few-shot learning. In this paper, we establish their potential in online adapting a batch trained neural network to domain-relevant labeled data at deployment time. We show that LMNs are better than other MANNs designed for meta-learning. We also found them to be more accurate and faster than state-of-the-art methods of retuning model parameters for adapting to domain-specific labeled data.