Jeffrey Li, Mohammadreza Armandpour, Seyed Iman Mirzadeh, Sachin Mehta, Vaishaal Shankar, Raviteja Vemulapalli, Samy Bengio, Oncel Tuzel, Mehrdad Farajtabar, Hadi Pouransari, Fartash Faghri. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Recent advancements in Large Language Models (LLMs) have sparked interest in their mathematical reasoning capabilities. While performance on the widely popular GSM8K benchmark has improved, questions remain about whether reported evaluation metrics are reliable, and reasoning abilities of LLMs have advanced. To overcome the limitations of existing evaluations, we introduce GSM-Symbolic, an improved benchmark created from symbolic templates that allow for the generation of a diverse set of questions. GSM-Symbolic enables more controllable evaluations, providing key insights and more reliable metrics for measuring the reasoning capabilities of models. Our findings reveal that LLMs exhibit noticeable variance when responding to different instantiations of the same question. Specifically, the performance of models declines when only the numerical values in the question are altered in the GSM-Symbolic benchmark. Furthermore, we investigate the fragility of mathematical reasoning in these models and demonstrate that their performance significantly deteriorates as the number of clauses in a question increases. We hypothesize that this decline is due to the fact that current LLMs are not capable of genuine logical reasoning; instead, they attempt to replicate the reasoning steps observed in their training data. When we add a single clause that appears relevant to the question, we observe significant performance drops (up to 65%) across all state-of-the-art models, even though the added clause does not contribute to the reasoning chain needed to reach the final answer. Overall, our work provides a more nuanced understanding of LLMs' capabilities and limitations in mathematical reasoning.

Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuning foundation models on one task often leads to the issue of *concept forgetting* on other tasks. Recent methods of robust fine-tuning aim to mitigate forgetting of prior knowledge without affecting the fine-tuning performance. Knowledge is often preserved by matching the original and fine-tuned model weights or feature pairs. However, such point-wise matching can be too strong, without explicit awareness of the feature neighborhood structures that encode rich knowledge as well. We propose a novel regularization method **Proxy-FDA** that explicitly preserves the structural knowledge in feature space. Proxy-FDA performs Feature Distribution Alignment (using nearest neighbor graphs) between the pre-trained and fine-tuned feature spaces, and the alignment is further improved by informative proxies that are generated dynamically to increase data diversity. Experiments show that Proxy-FDA significantly reduces concept forgetting during fine-tuning, and we find a strong correlation between forgetting and a distributional distance metric (in comparison to L2 distance). We further demonstrate Proxy-FDA's benefits in various fine-tuning settings (end-to-end, few-shot and continual tuning) and across different tasks like image classification, captioning and VQA.

Recent generations of frontier language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their fundamental capabilities, scaling properties, and limitations remain insufficiently understood. Current evaluations primarily focus on established mathematical and coding benchmarks, emphasizing final answer accuracy. However, this evaluation paradigm often suffers from data contamination and does not provide insights into the reasoning traces' structure and quality. In this work, we systematically investigate these gaps with the help of controllable puzzle environments that allow precise manipulation of compositional complexity while maintaining consistent logical structures. This setup enables the analysis of not only final answers but also the internal reasoning traces, offering insights into how LRMs ``think''. Through extensive experimentation across diverse puzzles, we show that frontier LRMs face a complete accuracy collapse beyond certain complexities. Moreover, they exhibit a counterintuitive scaling limit: their reasoning effort increases with problem complexity up to a point, then declines despite having an adequate token budget. By comparing LRMs with their standard LLM counterparts under equivalent inference compute, we identify three performance regimes: (1) low-complexity tasks where standard models surprisingly outperform LRMs, (2) medium-complexity tasks where additional thinking in LRMs demonstrates advantage, and (3) high-complexity tasks where both models experience complete collapse. We found that LRMs have limitations in exact computation: they fail to use explicit algorithms and reason inconsistently across scales and problems. We also investigate the reasoning traces in more depth, studying the patterns of explored solutions and analyzing the models' computational behavior, shedding light on their strengths, limitations, and ultimately raising questions about the nature for their reasoning capabilities.

Keivan Alizadeh, Seyed Iman Mirzadeh, Dmitry Belenko, S. Khatamifard, Minsik Cho, Carlo C Del Mundo, Mohammad Rastegari, Mehrdad Farajtabar. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Keeping large foundation models up to date on latest data is inherently expensive. To avoid the prohibitive costs of constantly retraining, it is imperative to continually train these models. This problem is exacerbated by the lack of any large scale continual learning benchmarks or baselines. We introduce the first set of web-scale Time-Continual (TiC) benchmarks for training vision-language models: TiC-DataComp, TiC-YFCC, and TiC-Redcaps. TiC-DataComp, our largest dataset, contains over 12.7B timestamped image-text pairs spanning 9 years (2014-2022). We first use our benchmarks to curate various dynamic evaluations to measure temporal robustness of existing models. We show OpenAI's CLIP (trained on data up to 2020) loses $\approx 8\%$ zero-shot accuracy on our curated retrieval task from 2021-2022 compared with more recently trained models in OpenCLIP repository. We then study how to efficiently train models on time-continuous data. We demonstrate that a simple rehearsal-based approach that continues training from the last checkpoint and replays old data reduces compute by $2.5\times$ when compared to the standard practice of retraining from scratch. Code is available at https://github.com/apple/ml-tic-clip.

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices. Despite recent trends favoring alternative activation functions such as GELU or SiLU, known for increased computation, this study strongly advocates for reinstating ReLU activation in LLMs. We demonstrate that using the ReLU activation function has a negligible impact on convergence and performance while significantly reducing computation and weight transfer. This reduction is particularly valuable during the memory-bound inference step, where efficiency is paramount. Exploring sparsity patterns in ReLU-based LLMs, we unveil the reutilization of activated neurons for generating new tokens and leveraging these insights, we propose practical strategies to substantially reduce LLM inference computation up to three times, using ReLU activations with minimal performance trade-offs.

Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot be deployed for many real-world applications. Motivated by this, we ask the following important question, "How can we leverage the knowledge from a large VFM to train a small task-specific model for a new target task with limited labeled training data?", and propose a simple task-oriented knowledge transfer approach as a highly effective solution to this problem. Our experimental results on five target tasks show that the proposed approach outperforms task-agnostic VFM distillation, web-scale CLIP pretraining, supervised ImageNet pretraining, and self-supervised DINO pretraining by up to 11.6%, 22.1%, 13.7%, and 29.8%, respectively. Furthermore, the proposed approach also demonstrates up to 9x, 4x and 15x reduction in pretraining compute cost when compared to task-agnostic VFM distillation, ImageNet pretraining and DINO pretraining, respectively, while outperforming them. We also show that the dataset used for transferring knowledge has a significant effect on the final target task performance, and introduce a retrieval-augmented knowledge transfer strategy that uses web-scale image retrieval to curate effective transfer sets.

We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no additional training cost for users. We propose a Dataset Reinforcement strategy based on data augmentation and knowledge distillation. Our generic strategy is designed based on extensive analysis across CNN- and transformer-based models and performing large-scale study of distillation with state-of-the-art models with various data augmentations. We create a reinforced version of the ImageNet training dataset, called ImageNet+, as well as reinforced datasets CIFAR-100+, Flowers-102+, and Food-101+. Models trained with ImageNet+are more accurate, robust, and calibrated, and transfer well to downstream tasks (e.g., segmentation and detection). As an example, the accuracy of ResNet-50 improves by 1.7% on the ImageNet validation set, 3.5% on ImageNetV2, and 10.0% on ImageNet-R. Expected Calibration Error (ECE) on the ImageNet validation set is also reduced by 9.9%. Using this backbone with Mask-RCNN for object detection on MS-COCO, the mean average precision improves by 0.8%. We reach similar gains for MobileNets, ViTs, and Swin-Transformers. For MobileNetV3 and Swin-Tiny, we observe significant improvements on ImageNet-R/A/C of up to 20% improved robustness. Models pretrained on ImageNet+and fine-tuned on CIFAR-100+, Flowers-102+, and Food-101+, reach up to 3.4% improved accuracy. The code, datasets, and pretrained models are available at https://github.com/apple/ml-dr.

Temporal data are ubiquitous in real-world applications, and they can be generally divided into two categories: 1) synchronous temporal data which are basically equivalent to time series data; and 2) the asynchronous data which are often in the form of event data with a time stamp in continuous time-space. In fact, the event data are often converted to the time series by aggregating the event count in equal time intervals in many previous approaches. While it is often of one’s greater interest to directly establish models based on the raw event data whose time stamps carry useful information, especially for those time-sensitive tasks, ranging from earthquake prediction, crime analysis, to infectious disease diffusion forecasting, etc. Developing the spatio-temporal point process and the related applications is the theme of this Special Issue, which treats an event as a point in the spatio-temporal space, with possibly extra attributes. The model captures the instantaneous happening rate of the events and their potential dependency. The derived use cases often refer to future events prediction, and causality estimation.

A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts. While the recent progress in continual learning literature is encouraging, our understanding of what properties of neural networks contribute to catastrophic forgetting is still limited. To address this, instead of focusing on continual learning algorithms, in this work, we focus on the model itself and study the impact of "width" of the neural network architecture on catastrophic forgetting, and show that width has a surprisingly significant effect on forgetting. To explain this effect, we study the learning dynamics of the network from various perspectives such as gradient orthogonality, sparsity, and lazy training regime. We provide potential explanations that are consistent with the empirical results across different architectures and continual learning benchmarks.

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teacher) pre-trained network is used to train a smaller (student) network. However, in this paper, we show that the student network performance degrades when the gap between student and teacher is large. Given a fixed student network, one cannot employ an arbitrarily large teacher, or in other words, a teacher can effectively transfer its knowledge to students up to a certain size, not smaller. To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher. Moreover, we study the effect of teacher assistant size and extend the framework to multi-step distillation. Theoretical analysis and extensive experiments on CIFAR-10,100 and ImageNet datasets and on CNN and ResNet architectures substantiate the effectiveness of our proposed approach.

Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks suffer from the problem of catastrophic forgetting; they forget how to solve previous tasks after being trained on a new task, despite having the essential capacity to solve both tasks if they were trained on both simultaneously. In this paper, we propose to address this issue from a parameter space perspective and study an approach to restrict the direction of the gradient updates to avoid forgetting previously-learned data. We present the Orthogonal Gradient Descent (OGD) method, which accomplishes this goal by projecting the gradients from new tasks onto a subspace in which the neural network output on previous task does not change and the projected gradient is still in a useful direction for learning the new task. Our approach utilizes the high capacity of a neural network more efficiently and does not require storing the previously learned data that might raise privacy concerns. Experiments on common benchmarks reveal the effectiveness of the proposed OGD method.

This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs). For MDPs that are ergodic and linear (i.e. where rewards and dynamics are linear in some known features), we provide the first finite-sample OPE error bound, extending the existing results beyond the episodic and discounted cases. In a more general setting, when the feature dynamics are approximately linear and for arbitrary rewards, we propose a new approach for estimating stationary distributions with function approximation. We formulate this problem as finding the maximum-entropy distribution subject to matching feature expectations under empirical dynamics. We show that this results in an exponential-family distribution whose sufficient statistics are the features, paralleling maximum-entropy approaches in supervised learning. We demonstrate the effectiveness of the proposed OPE approaches in multiple environments.

Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly plastic, lacking the stability necessary to prevent the forgetting of previous knowledge, which means that as learning progresses, networks tend to forget previously seen tasks. This phenomenon coined in the continual learning literature, has attracted much attention lately, and several families of approaches have been proposed with different degrees of success. However, there has been limited prior work extensively analyzing the impact that different training regimes -- learning rate, batch size, regularization method-- can have on forgetting. In this work, we depart from the typical approach of altering the learning algorithm to improve stability. Instead, we hypothesize that the geometrical properties of the local minima found for each task play an important role in the overall degree of forgetting. In particular, we study the effect of dropout, learning rate decay, and batch size on forming training regimes that widen the tasks' local minima and consequently, on helping it not to forget catastrophically. Our study provides practical insights to improve stability via simple yet effective techniques that outperform alternative baselines.

Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in predictions of the trained model as new target values for retraining (and iterate this loop possibly a few times). It has been empirically observed that the self-distilled model often achieves higher accuracy on held out data. Why this happens, however, has been a mystery: the self-distillation dynamics does not receive any new information about the task and solely evolves by looping over training. To the best of our knowledge, there is no rigorous understanding of why this happens. This work provides the first theoretical analysis of self-distillation. We focus on fitting a nonlinear function to training data, where the model space is Hilbert space and fitting is subject to L2 regularization in this function space. We show that self-distillation iterations modify regularization by progressively limiting the number of basis functions that can be used to represent the solution. This implies (as we also verify empirically) that while a few rounds of self-distillation may reduce over-fitting, further rounds may lead to under-fitting and thus worse performance.

The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined extrinsic reward function. However, a long-term question inevitably arises: how will such independent agents cooperate when they are continually learning and acting in a shared multi-agent environment? Observing that humans often provide incentives to influence others' behavior, we propose to equip each RL agent in a multi-agent environment with the ability to give rewards directly to other agents, using a learned incentive function. Each agent learns its own incentive function by explicitly accounting for its impact on the learning of recipients and, through them, the impact on its own extrinsic objective. We demonstrate in experiments that such agents significantly outperform standard RL and opponent-shaping agents in challenging general-sum Markov games, often by finding a near-optimal division of labor. Our work points toward more opportunities and challenges along the path to ensure the common good in a multi-agent future.

Poisson Factorization (PF) is the gold standard framework for recommendation systems with implicit feedback whose variants show state-of-the-art performance on real-world recommendation tasks. However, they do not explicitly take into account the temporal behavior of users which is essential to recommend the right item to the right user at the right time. In this paper, we introduce Recurrent Poisson Factorization (RPF) framework that generalizes the classical PF methods by utilizing a Poisson process for modeling the implicit feedback. RPF treats time as a natural constituent of the model, and takes important factors for recommendation into consideration to provide a rich family of time-sensitive factorization models. They include Hierarchical RPFthat captures the consumption heterogeneity among users and items, Dynamic RPF that handles dynamic user preferences and item specifications, Social RPF that models the social-aspect of product adoption, Item-Item RPFthat considers the inter-item correlations, and eXtended Item-Item RPF that utilizes items' metadata to better infer the correlation among engagement patterns of users with items. We also develop an efficient variational algorithm for approximate inference that scales up to massive datasets. We demonstrate RPF's superior performance over many state-of-the-art methods on synthetic dataset, and wide variety of large scale real-world datasets.

The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL). Street View can be a sensible testbed for such RL agents, because it provides real-world photographic imagery at ground level, with diverse street appearances; it has been made into an interactive environment called StreetLearn and used for research on navigation. However, goal-driven street navigation agents have not so far been able to transfer to unseen areas without extensive retraining, and relying on simulation is not a scalable solution. Since aerial images are easily and globally accessible, we propose instead to transfer a ground view policy, from training areas to unseen (target) parts of the city, by utilizing aerial view observations. Our core idea is to pair the ground view with an aerial view and to learn a joint policy that is transferable across views. We achieve this by learning a similar embedding space for both views, distilling the policy across views and dropping out visual modalities. We further reformulate the transfer learning paradigm into three stages: 1) cross-modal training, when the agent is initially trained on multiple city regions, 2) aerial view-only adaptation to a new area, when the agent is adapted to a held-out region using only the easily obtainable aerial view, and 3) ground view-only transfer, when the agent is tested on navigation tasks on unseen ground views, without aerial imagery. Our experimental results suggest that the proposed cross-view policy learning enables better generalization of the agent and allows for more effective transfer to unseen environments.The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL). Street View can be a sensible testbed for such RL agents, because it provides real-world photographic imagery at ground level, with diverse street appearances; it has been made into an interactive environment called StreetLearn and used for research on navigation. However, goal-driven street navigation agents have not so far been able to transfer to unseen areas without extensive retraining, and relying on simulation is not a scalable solution. Since aerial images are easily and globally accessible, we propose instead to train a multi-modal policy on ground and aerial views, then transfer the ground view policy to unseen (target) parts of the city by utilizing aerial view observations. Our core idea is to pair the ground view with an aerial view and to learn a joint policy that is transferable across views. We achieve this by learning a similar embedding space for both views, distilling the policy across views and dropping out visual modalities. We further reformulate the transfer learning paradigm into three stages: 1) cross-modal training, when the agent is initially trained on multiple city regions, 2) aerial view-only adaptation to a new area, when the agent is adapted to a held-out region using only the easily obtainable aerial view, and 3) ground view-only transfer, when the agent is tested on navigation tasks on unseen ground views, without aerial imagery. Experimental results suggest that the proposed cross-view policy learning enables better generalization of the agent and allows for more effective transfer to unseen environments.

Real-world sequential data are often generated based on complicated and latent mechanisms, which can be formulated as event sequences occurring in the continuous time domain. In addition, continuous signals may often be associated with event sequences and be formulated as time series with fixed time lags. Traditionally, event sequences are often modeled by parametric temporal point processes, which use explicitly defined conditional intensity functions to quantify the occurrence rates of events. However, these parametric models often merely take one-side information from event sequences into account while ignoring the information from concurrent time series, and their intensity functions are usually designed for specific tasks dependent on prior knowledge. To tackle the above-mentioned problems, we propose a model called recurrent point process networks which instantiates temporal point process models with temporal recurrent neural networks (RNNs). In particular, the intensity functions of the proposed model are modeled by two RNNs: one temporal RNN capturing the relationships among events and the other RNN updating intensity functions based on time series. Furthermore, an attention mechanism is introduced, which uncovers influence strengths among events with good interpretability. Focusing on challenging tasks such as temporal event prediction and underlying relational network mining, we demonstrate the superiority of our model on both synthetic and real-world data.

Estimating the future event sequence conditioned on current observations is a long-standing and challenging task in temporal analysis. On one hand for many real-world problems the underlying dynamics can be very complex and often unknown. This renders the traditional parametric point process models often fail to fit the data for their limited capacity. On the other hand, long-term prediction suffers from the problem of bias exposure where the error accumulates and propagates to future prediction. Our new model builds upon the sequence to sequence (seq2seq) prediction network. Compared with parametric point process models, its modeling capacity is higher and has better flexibility for fitting real-world data. The main novelty of the paper is to mitigate the second challenge by introducing the likelihood-free loss based on Wasserstein distance between point processes, besides negative maximum likelihood loss used in the traditional seq2seq model. Wasserstein distance, unlike KL divergence i.e. MLE loss, is sensitive to the underlying geometry between samples and can robustly enforce close geometry structure between them. This technique is proven able to improve the vanilla seq2seq model by a notable margin on various tasks.

We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time. Although the accuracy of the model has a huge impact on the overall performance of DR, most of the work on using the DR estimators in OPE has been focused on improving the IS part, and not much on how to learn the model. In this paper, we propose alternative DR estimators, called more robust doubly robust (MRDR), that learn the model parameter by minimizing the variance of the DR estimator. We first present a formulation for learning the DR model in RL. We then derive formulas for the variance of the DR estimator in both contextual bandits and RL, such that their gradients w.r.t. the model parameters can be estimated from the samples, and propose methods to efficiently minimize the variance. We prove that the MRDR estimators are strongly consistent and asymptotically optimal. Finally, we evaluate MRDR in bandits and RL benchmark problems, and compare its performance with the existing methods.

The spread of invasive species to new areas threatens the stability of ecosystems and causes major economic losses. We propose a novel approach to minimize the spread of an invasive species given a limited intervention budget. We first model invasive species spread using Hawkes processes, and then derive closed-form expressions for characterizing the effect of an intervention action on the invasion process. We use this to obtain an optimal intervention plan based on an integer programming formulation, and compare the optimal plan against several ecologically-motivated heuristic strategies used in practice. We present an empirical study of two variants of the invasive control problem: minimizing the final rate of invasions, and minimizing the number of invasions at the end of a given time horizon. The optimized intervention achieves nearly the same level of control that would be attained by completely eradicating the species, but at only 60-80\% of the cost.

In real world social networks, there are multiple cascades which are rarely independent. They usually compete or cooperate with each other. Motivated by the reinforcement theory in sociology we leverage the fact that adoption of a user to any behavior is modeled by the aggregation of behaviors of its neighbors. We use a multidimensional marked Hawkes process to model users product adoption and consequently spread of cascades in social networks. The resulting inference problem is proved to be convex and is solved in parallel by using the barrier method. The advantage of the proposed model is twofold; it models correlated cascades and also learns the latent diffusion network. Experimental results on synthetic and two real datasets gathered from Twitter, URL shortening and music streaming services, illustrate the superior performance of the proposed model over the alternatives.

We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model. The spread of fake news and mitigation events within the network is modeled by a multivariate Hawkes process with additional exogenous control terms. By choosing a feature representation of states, defining mitigation actions and constructing reward functions to measure the effectiveness of mitigation activities, we map the problem of fake news mitigation into the reinforcement learning framework. We develop a policy iteration method unique to the multivariate networked point process, with the goal of optimizing the actions for maximal reward under budget constraints. Our method shows promising performance in real-time intervention experiments on a Twitter network to mitigate a surrogate fake news campaign, and outperforms alternatives on synthetic datasets.

Poisson factorization is a probabilistic model of users and items for recommendation systems, where the so-called implicit consumer data is modeled by a factorized Poisson distribution. There are many variants of Poisson factorization methods who show state-of-the-art performance on real-world recommendation tasks. However, most of them do not explicitly take into account the temporal behavior and the recurrent activities of users which is essential to recommend the right item to the right user at the right time. In this paper, we introduce Recurrent Poisson Factorization (RPF) framework that generalizes the classical PF methods by utilizing a Poisson process for modeling the implicit feedback. RPF treats time as a natural constituent of the model and brings to the table a rich family of time-sensitive factorization models. To elaborate, we instantiate several variants of RPF who are capable of handling dynamic user preferences and item specification (DRPF), modeling the social-aspect of product adoption (SRPF), and capturing the consumption heterogeneity among users and items (HRPF). We also develop a variational algorithm for approximate posterior inference that scales up to massive data sets. Furthermore, we demonstrate RPF's superior performance over many state-of-the-art methods on synthetic dataset, and large scale real-world datasets on music streaming logs, and user-item interactions in M-Commerce platforms.

Point processes are becoming very popular in modeling asynchronous sequential data due to their sound mathematical foundation and strength in modeling a variety of real-world phenomena. Currently, they are often characterized via intensity function which limits model's expressiveness due to unrealistic assumptions on its parametric form used in practice. Furthermore, they are learned via maximum likelihood approach which is prone to failure in multi-modal distributions of sequences. In this paper, we propose an intensity-free approach for point processes modeling that transforms nuisance processes to a target one. Furthermore, we train the model using a likelihood-free leveraging Wasserstein distance between point processes. Experiments on various synthetic and real-world data substantiate the superiority of the proposed point process model over conventional ones.

Online knowledge repositories typically rely on their users or dedicated editors to evaluate the reliability of their contents. These explicit feedback mechanisms can be viewed as noisy measurements of both information reliability and information source trustworthiness. Can we leverage these noisy measurements, often biased, to distill a robust, unbiased and interpretable measure of both notions?

Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it. Online users are constantly creating new links when exposed to new information sources, and in turn these links are alternating the way information spreads. However, these two highly intertwined stochastic processes, information diffusion and network evolution, have been predominantly studied separately, ignoring their co-evolutionary dynamics. We propose a temporal point process model, Coevolve, for such joint dynamics, allowing the intensity of one process to be modulated by that of the other. This model allows us to efficiently simulate interleaved diffusion and network events, and generate traces obeying common diffusion and network patterns observed in real-world networks such as Twitter. Furthermore, we also develop a convex optimization framework to learn the parameters of the model from historical diffusion and network evolution traces. We experimented with both synthetic data and data gathered from Twitter, and show that our model provides a good fit to the data as well as more accurate predictions than alternatives.

Learning Granger causality for general point processes is a very challenging task. We propose an effective method learning Granger causality for a special but significant type of point processes — Hawkes processes. Focusing on Hawkes processes, we reveal the relationship between Hawkes process’s impact functions and its Granger causality graph. Specifically, our model represents impact functions using a series of basis functions and recovers the Granger causality graph via group sparsity of the impact functions’ coefficients. We propose an effective learning algorithm combining a maximum likelihood estimator (MLE) with a sparse-group-lasso (SGL) regularizer. Additionally, the pairwise similarity between the dimensions of the process is considered when their clustering structure is available. We analyze our learning method and discuss the selection of the basis functions. Experiments on synthetic data and real-world data show that our method can learn the Granger causality graph and the triggering patterns of Hawkes processes simultaneously.

Many users in online social networks are constantly trying to gain attention from their followers by broadcasting posts to them. These broadcasters are likely to gain greater attention if their posts can remain visible for a longer period of time among their followers' most recent feeds. Then when to post? In this paper, we study the problem of smart broadcasting using the framework of temporal point processes, where we model users feeds and posts as discrete events occurring in continuous time. Based on such continuous-time model, then choosing a broadcasting strategy for a user becomes a problem of designing the conditional intensity of her posting events. We derive a novel formula which links this conditional intensity with the visibility of the user in her followers' feeds. Furthermore, by exploiting this formula, we develop an efficient convex optimization framework for the when-to-post problem. Our method can find broadcasting strategies that reach a desired visibility level with provable guarantees. We experimented with data gathered from Twitter, and show that our framework can consistently make broadcasters' post more visible than alternatives.

We consider control problems for multi-stage campaigning over social networks. The dynamic programming framework is employed to balance the high present reward and large penalty on low future outcome in the presence of extensive uncertainties. In particular, we establish theoretical foundations of optimal campaigning over social networks where the user activities are modeled as a multivariate Hawkes process, and we derive a time dependent linear relation between the intensity of exogenous events and several commonly used objective functions of campaigning. We further develop a convex dynamic programming framework for determining the optimal intervention policy that prescribes the required level of external drive at each stage for the desired campaigning result. Experiments on both synthetic data and the real-world MemeTracker dataset show that our algorithm can steer the user activities for optimal campaigning much more accurately than baselines.

When a piece of malicious information becomes rampant in an information diffusion network, can we identify the source node that originally introduced the piece into the network and infer the time when it initiated this? Being able to do so is critical for curtailing the spread of malicious information, and reducing the potential losses incurred. This is a very challenging problem since typically only incomplete traces are observed and we need to unroll the incomplete traces into the past in order to pinpoint the source. In this paper, we tackle this problem by developing a two-stage framework, which first learns a continuous-time diffusion network based on historical diffusion traces and then identifies the source of an incomplete diffusion trace by maximizing the likelihood of the trace under the learned model. Experiments on both large synthetic and real-world data show that our framework can effectively go back to the past, and pinpoint the source node and its initiation time significantly more accurately than previous state-of-the-arts.

Clusters in document streams, such as online news articles, can be induced by their textual contents, as well as by the temporal dynamics of their arriving patterns. Can we leverage both sources of information to obtain a better clustering of the documents, and distill information that is not possible to extract using contents only? In this paper, we propose a novel random process, referred to as the Dirichlet-Hawkes process, to take into account both information in a unified framework. A distinctive feature of the proposed model is that the preferential attachment of items to clusters according to cluster sizes, present in Dirichlet processes, is now driven according to the intensities of cluster-wise self-exciting temporal point processes, the Hawkes processes. This new model establishes a previously unexplored connection between Bayesian Nonparametrics and temporal Point Processes, which makes the number of clusters grow to accommodate the increasing complexity of online streaming contents, while at the same time adapts to the ever changing dynamics of the respective continuous arrival time. We conducted large-scale experiments on both synthetic and real world news articles, and show that Dirichlet-Hawkes processes can recover both meaningful topics and temporal dynamics, which leads to better predictive performance in terms of content perplexity and arrival time of future documents.

Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it. Online users are constantly creating new links when exposed to new information sources, and in turn these links are alternating the way information spreads. However, these two highly intertwined stochastic processes, information diffusion and network evolution, have been predominantly studied separately, ignoring their co-evolutionary dynamics.We propose a temporal point process model, COEVOLVE, for such joint dynamics, allowing the intensity of one process to be modulated by that of the other. This model allows us to efficiently simulate interleaved diffusion and network events, and generate traces obeying common diffusion and network patterns observed in real-world networks. Furthermore, we also develop a convex optimization framework to learn the parameters of the model from historical diffusion and network evolution traces. We experimented with both synthetic data and data gathered from Twitter, and show that our model provides a good fit to the data as well as more accurate predictions than alternatives.

The real social network and associated communities are often hidden under the declared friend or group lists in social networks. We usually observe the manifestation of these hidden networks and communities in the form of recurrent and time-stamped individuals' activities in the social network. Inferring the underlying network and finding coherent communities are therefore two key challenges in social networks analysis. In this paper, we address the following question: Could we simultaneously detect community structure and network infectivity among individuals from their activities? Based on the fact that the two characteristics intertwine and that knowing one will help better revealing the other, we propose a multidimensional Hawkes process that can address them simultaneously. To this end, we parametrize the network infectivity in terms of individuals' participation in communities and the popularity of each individual. We show that this modeling approach has many benefits, both conceptually and experimentally. We utilize Bayesian variational inference to design NetCodec, an efficient inference algorithm which is verified with both synthetic and real world data sets. The experiments show that NetCodec can discover the underlying network infectivity and community structure more accurately than baseline method.

We consider the problem of determining the structural differences between different types of social networks and using these differences for applications concerning prediction of their structures. Much research on this problem has been conducted in the context of social media such as Facebook and Twitter, within which one would like to characterize and classify different types of individuals such as leaders, followers, and influencers. However, we consider the problem in the context of information gathered from law-enforcement agencies, financial institutions, and similar organizations, within which one would like to characterize and classify different types of persons of interest. The members of these networks tend to form special communities and thus new techniques are required. We propose a new generative model called Cliqster, for unweighted networks, and we describe an interpretable, and efficient algorithm for representing networks within this model. Our representation preserves the important underlying characteristics of the network and is both concise and discriminative. We demonstrate the discriminative power of our method by comparing to a traditional SVD method as well as a state-of-the-art Graphlet algorithm. Our results are general in that they can be applied to “person of interest” networks as well as traditional social media networks.

Bag of words models for feature extraction have demonstrated top-notch performance in image classification. These representations are usually accompanied by a coding method. Recently, methods that code a descriptor giving regard to its nearby bases have proved efficacious. These methods take into account the nonlinear structure of descriptors, since local similarities are a good approximation of global similarities. However, they confine their usage of the global similarities to nearby bases. In this paper, we propose a coding scheme that brings into focus the manifold structure of descriptors, and devise a method to compute the global similarities of descriptors to the bases. Given a local similarity measure between bases, a global measure is computed. Exploiting the local similarity of a descriptor and its nearby bases, a global measure of association of a descriptor to all the bases is computed. Unlike the locality-based and sparse coding methods, the proposed coding varies smoothly with respect to the underlying manifold. Experiments on benchmark image classification datasets substantiate the superiority of the proposed method over its locality and sparsity based rivals.